1
|
Roberts L, Lanes S, Peatman O, Assheton P. The importance of SNOMED CT concept specificity in healthcare analytics. HEALTH INF MANAG J 2024; 53:157-165. [PMID: 36680531 DOI: 10.1177/18333583221144662] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
Abstract
BACKGROUND Healthcare data frequently lack the specificity level needed to achieve clinical and operational objectives such as optimising bed management. Pneumonia is a disease of importance as it accounts for more bed days than any other lung disease and has a varied aetiology. The condition has a range of SNOMED CT concepts with different levels of specificity. OBJECTIVE This study aimed to quantify the importance of the specificity of an SNOMED CT concept, against well-established predictors, for forecasting length of stay for pneumonia patients. METHOD A retrospective data analysis was conducted of pneumonia admissions to a tertiary hospital between 2011 and 2021. For inclusion, the primary diagnosis was a subtype of bacterial or viral pneumonia, as identified by SNOMED CT concepts. Three linear mixed models were constructed. Model One included known predictors of length of stay. Model Two included the predictors in Model One and SNOMED CT concepts of lower specificity. Model Three included the Model Two predictors and the concepts with higher specificity. Model performances were compared. RESULTS Sex, ethnicity, deprivation rank and Charlson Comorbidity Index scores (age-adjusted) were meaningful predictors of length of stay in all models. Inclusion of lower specificity SNOMED CT concepts did not significantly improve performance (ΔR2 = 0.41%, p = .058). SNOMED CT concepts with higher specificity explained more variance than each of the individual predictors (ΔR2 = 4.31%, p < .001). CONCLUSION SNOMED CT concepts with higher specificity explained more variance in length of stay than a range of well-studied predictors. IMPLICATIONS Accurate and specific clinical documentation using SNOMED CT can improve predictive modelling and the generation of actionable insights. Resources should be dedicated to optimising and assuring clinical documentation quality at the point of recording.
Collapse
Affiliation(s)
- Luke Roberts
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Sadie Lanes
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | | | - Phil Assheton
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| |
Collapse
|
2
|
Jain R, Singh M, Rao AR, Garg R. Predicting hospital length of stay using machine learning on a large open health dataset. BMC Health Serv Res 2024; 24:860. [PMID: 39075382 PMCID: PMC11288104 DOI: 10.1186/s12913-024-11238-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Accepted: 06/24/2024] [Indexed: 07/31/2024] Open
Abstract
BACKGROUND Governments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient's length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper. METHODS We investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns. RESULTS The study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns. CONCLUSION Our study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery.
Collapse
Affiliation(s)
- Raunak Jain
- Indian Institute of Technology, Delhi, India
| | | | | | - Rahul Garg
- Indian Institute of Technology, Delhi, India
| |
Collapse
|
3
|
Scala A, Trunfio TA, Improta G. The classification algorithms to support the management of the patient with femur fracture. BMC Med Res Methodol 2024; 24:150. [PMID: 39014322 PMCID: PMC11251118 DOI: 10.1186/s12874-024-02276-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 07/05/2024] [Indexed: 07/18/2024] Open
Abstract
Effectiveness in health care is a specific characteristic of each intervention and outcome evaluated. Especially with regard to surgical interventions, organization, structure and processes play a key role in determining this parameter. In addition, health care services by definition operate in a context of limited resources, so rationalization of service organization becomes the primary goal for health care management. This aspect becomes even more relevant for those surgical services for which there are high volumes. Therefore, in order to support and optimize the management of patients undergoing surgical procedures, the data analysis could play a significant role. To this end, in this study used different classification algorithms for characterizing the process of patients undergoing surgery for a femoral neck fracture. The models showed significant accuracy with values of 81%, and parameters such as Anaemia and Gender proved to be determined risk factors for the patient's length of stay. The predictive power of the implemented model is assessed and discussed in view of its capability to support the management and optimisation of the hospitalisation process for femoral neck fracture, and is compared with different model in order to identify the most promising algorithms. In the end, the support of artificial intelligence algorithms laying the basis for building more accurate decision-support tools for healthcare practitioners.
Collapse
Affiliation(s)
- Arianna Scala
- Department of Public Health, University of Naples "Federico II", Naples, Italy
| | - Teresa Angela Trunfio
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Naples, Italy.
| | - Giovanni Improta
- Department of Public Health, University of Naples "Federico II", Naples, Italy
- Interdepartmental Research Center on Management and Innovation in Healthcare, University of Naples "Federico II", Naples, Italy
| |
Collapse
|
4
|
Stretton B, Booth AEC, Satheakeerthy S, Howson S, Evans S, Kovoor J, Akram W, McNeil K, Hopkins A, Zeitz K, Leslie A, Psaltis P, Gupta A, Tan S, Teo M, Vanlint A, Chan WO, Zannettino A, O'Callaghan PG, Maddison J, Gluck S, Gilbert T, Bacchi S. Translational artificial intelligence-led optimization and realization of estimated discharge with a supportive weekend interprofessional flow team (TAILORED-SWIFT). Intern Emerg Med 2024:10.1007/s11739-024-03689-2. [PMID: 38907756 DOI: 10.1007/s11739-024-03689-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/29/2024] [Accepted: 06/17/2024] [Indexed: 06/24/2024]
Abstract
Weekend discharges occur less frequently than discharges on weekdays, contributing to hospital congestion. Artificial intelligence algorithms have previously been derived to predict which patients are nearing discharge based upon ward round notes. In this implementation study, such an artificial intelligence algorithm was coupled with a multidisciplinary discharge facilitation team on weekend shifts. This approach was implemented in a tertiary hospital, and then compared to a historical cohort from the same time the previous year. There were 3990 patients included in the study. There was a significant increase in the proportion of inpatients who received weekend discharges in the intervention group compared to the control group (median 18%, IQR 18-20%, vs median 14%, IQR 12% to 17%, P = 0.031). There was a corresponding higher absolute number of weekend discharges during the intervention period compared to the control period (P = 0.025). The studied intervention was associated with an increase in weekend discharges and economic analyses support this approach as being cost-effective. Further studies are required to examine the generalizability of this approach to other centers.
Collapse
Affiliation(s)
- Brandon Stretton
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Andrew E C Booth
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Shrirajh Satheakeerthy
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Sarah Howson
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Shaun Evans
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Joshua Kovoor
- University of Adelaide, Adelaide, SA, 5005, Australia
- Ballarat Base Hospital, Ballarat Vic, Australia
| | - Waqas Akram
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
| | - Keith McNeil
- Commission On Excellence and Innovation in Health, Adelaide, SA, 5000, Australia
| | | | - Kathryn Zeitz
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Alasdair Leslie
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Peter Psaltis
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - Aashray Gupta
- Royal North Shore Hospital, St Leonard's, NSW, 2065, Australia
| | - Sheryn Tan
- University of Adelaide, Adelaide, SA, 5005, Australia
| | - Melissa Teo
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
| | - Andrew Vanlint
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
| | - Weng Onn Chan
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | | | - Patrick G O'Callaghan
- SA Health, Adelaide, SA, 5000, Australia
- Royal Adelaide Hospital, Adelaide, SA, 5000, Australia
| | - John Maddison
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
| | - Samuel Gluck
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
| | - Toby Gilbert
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia
- SA Health, Adelaide, SA, 5000, Australia
- University of Adelaide, Adelaide, SA, 5005, Australia
| | - Stephen Bacchi
- Lyell McEwin Hospital, Elizabeth Vale, SA, 5112, Australia.
- SA Health, Adelaide, SA, 5000, Australia.
- University of Adelaide, Adelaide, SA, 5005, Australia.
- Flinders University, Bedford Park, SA, 5042, Australia.
| |
Collapse
|
5
|
AlMuhaideb S, bin Shawyah A, Alhamid MF, Alabbad A, Alabbad M, Alsergani H, Alswailem O. Beyond the Bedside: Machine Learning-Guided Length of Stay (LOS) Prediction for Cardiac Patients in Tertiary Care. Healthcare (Basel) 2024; 12:1110. [PMID: 38891185 PMCID: PMC11171809 DOI: 10.3390/healthcare12111110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2024] [Revised: 05/19/2024] [Accepted: 05/28/2024] [Indexed: 06/21/2024] Open
Abstract
Efficient management of hospital resources is essential for providing high-quality healthcare while ensuring sustainability. Length of stay (LOS), measuring the duration from admission to discharge, directly impacts patient outcomes and resource utilization. Accurate LOS prediction offers numerous benefits, including reducing re-admissions, ensuring appropriate staffing, and facilitating informed discharge planning. While conventional methods rely on statistical models and clinical expertise, recent advances in machine learning (ML) present promising avenues for enhancing LOS prediction. This research focuses on developing an ML-based LOS prediction model trained on a comprehensive real-world dataset and discussing the important factors towards practical deployment of trained ML models in clinical settings. This research involves the development of a comprehensive adult cardiac patient dataset (SaudiCardioStay (SCS)) from the King Faisal Specialist Hospital & Research Centre (KFSH&RC) hospital in Saudi Arabia, comprising 4930 patient encounters for 3611 unique patients collected from 2019 to 2022 (excluding 2020). A diverse range of classical ML models (i.e., Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), artificial neural networks (ANNs), Average Voting Regression (AvgVotReg)) are implemented for the SCS dataset to explore the potential of existing ML models in LOS prediction. In addition, this study introduces a novel approach for LOS prediction by incorporating a dedicated LOS classifier within a sophisticated ensemble methodology (i.e., Two-Level Sequential Cascade Generalization (2LSCG), Three-Level Sequential Cascade Generalization (3LSCG), Parallel Cascade Generalization (PCG)), aiming to enhance prediction accuracy and capture nuanced patterns in healthcare data. The experimental results indicate the best mean absolute error (MAE) of 0.1700 for the 3LSCG model. Relatively comparable performance was observed for the AvgVotReg model, with a MAE of 0.1703. In the end, a detailed analysis of the practical implications, limitations, and recommendations concerning the deployment of ML approaches in actual clinical settings is presented.
Collapse
Affiliation(s)
- Sarab AlMuhaideb
- Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 266, Riyadh 11362, Saudi Arabia;
| | - Alanoud bin Shawyah
- Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 266, Riyadh 11362, Saudi Arabia;
| | - Mohammed F. Alhamid
- Healthcare Information Technology Affairs (HITA), King Faisal Specialist Hospital & Research Center, P.O. Box 3354, Riyadh 11211, Saudi Arabia; (M.F.A.); (A.A.); (M.A.); (O.A.)
| | - Arwa Alabbad
- Healthcare Information Technology Affairs (HITA), King Faisal Specialist Hospital & Research Center, P.O. Box 3354, Riyadh 11211, Saudi Arabia; (M.F.A.); (A.A.); (M.A.); (O.A.)
| | - Maram Alabbad
- Healthcare Information Technology Affairs (HITA), King Faisal Specialist Hospital & Research Center, P.O. Box 3354, Riyadh 11211, Saudi Arabia; (M.F.A.); (A.A.); (M.A.); (O.A.)
| | - Hani Alsergani
- Heart Center, King Faisal Specialist Hospital & Research Center, P.O. Box 3354, Riyadh 11211, Saudi Arabia;
| | - Osama Alswailem
- Healthcare Information Technology Affairs (HITA), King Faisal Specialist Hospital & Research Center, P.O. Box 3354, Riyadh 11211, Saudi Arabia; (M.F.A.); (A.A.); (M.A.); (O.A.)
| |
Collapse
|
6
|
Chang Junior J, Caneo LF, Turquetto ALR, Amato LP, Arita ECTC, Fernandes AMDS, Trindade EM, Jatene FB, Dossou PE, Jatene MB. Predictors of in-ICU length of stay among congenital heart defect patients using artificial intelligence model: A pilot study. Heliyon 2024; 10:e25406. [PMID: 38370176 PMCID: PMC10869777 DOI: 10.1016/j.heliyon.2024.e25406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2023] [Revised: 01/23/2024] [Accepted: 01/25/2024] [Indexed: 02/20/2024] Open
Abstract
Objective This study aims to develop a predictive model using artificial intelligence to estimate the ICU length of stay (LOS) for Congenital Heart Defects (CHD) patients after surgery, improving care planning and resource management. Design We analyze clinical data from 2240 CHD surgery patients to create and validate the predictive model. Twenty AI models are developed and evaluated for accuracy and reliability. Setting The study is conducted in a Brazilian hospital's Cardiovascular Surgery Department, focusing on transplants and cardiopulmonary surgeries. Participants Retrospective analysis is conducted on data from 2240 consecutive CHD patients undergoing surgery. Interventions Ninety-three pre and intraoperative variables are used as ICU LOS predictors. Measurements and main results Utilizing regression and clustering methodologies for ICU LOS (ICU Length of Stay) estimation, the Light Gradient Boosting Machine, using regression, achieved a Mean Squared Error (MSE) of 15.4, 11.8, and 15.2 days for training, testing, and unseen data. Key predictors included metrics such as "Mechanical Ventilation Duration", "Weight on Surgery Date", and "Vasoactive-Inotropic Score". Meanwhile, the clustering model, Cat Boost Classifier, attained an accuracy of 0.6917 and AUC of 0.8559 with similar key predictors. Conclusions Patients with higher ventilation times, vasoactive-inotropic scores, anoxia time, cardiopulmonary bypass time, and lower weight, height, BMI, age, hematocrit, and presurgical oxygen saturation have longer ICU stays, aligning with existing literature.
Collapse
Affiliation(s)
- João Chang Junior
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Escola Superior de Engenharia e Gestão - ESEG, Rua Apeninos, 960, São Paulo, Brazil
- Centro Universitário Armando Alvares Penteado - FAAP, Rua Alagoas, 903, São Paulo, Brazil
| | - Luiz Fernando Caneo
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Aida Luiza Ribeiro Turquetto
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
| | - Luciana Patrick Amato
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
| | - Elisandra Cristina Trevisan Calvo Arita
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Alfredo Manoel da Silva Fernandes
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Evelinda Marramon Trindade
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
- Laboratório de Ensino, Pesquisa e Inovação Em Saúde - LEPIC-HCFMUSP, Superintendência / Hospital Das Clínicas da FMUSP, Rua Dr. Ovidio Pires de Campos, 225, 5°. Andar – Superintendência, Sao Paulo, Brazil
- Sao Paulo State Health Secretariat–SES-SP, Sao Paulo, Brazil
| | - Fábio Biscegli Jatene
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Paul-Eric Dossou
- Institut Catholique des Arts et Metiers–Icam, Paris-Senart, France
| | - Marcelo Biscegli Jatene
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| |
Collapse
|
7
|
Ricciardi C, Marino MR, Trunfio TA, Majolo M, Romano M, Amato F, Improta G. Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study. Front Digit Health 2024; 5:1323849. [PMID: 38259256 PMCID: PMC10800466 DOI: 10.3389/fdgth.2023.1323849] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Accepted: 12/15/2023] [Indexed: 01/24/2024] Open
Abstract
Background Recently, crowding in emergency departments (EDs) has become a recognised critical factor impacting global public healthcare, resulting from both the rising supply/demand mismatch in medical services and the paucity of hospital beds available in inpatients units and EDs. The length of stay in the ED (ED-LOS) has been found to be a significant indicator of ED bottlenecks. The time a patient spends in the ED is quantified by measuring the ED-LOS, which can be influenced by inefficient care processes and results in increased mortality and health expenditure. Therefore, it is critical to understand the major factors influencing the ED-LOS through forecasting tools enabling early improvements. Methods The purpose of this work is to use a limited set of features impacting ED-LOS, both related to patient characteristics and to ED workflow, to predict it. Different factors were chosen (age, gender, triage level, time of admission, arrival mode) and analysed. Then, machine learning (ML) algorithms were employed to foresee ED-LOS. ML procedures were implemented taking into consideration a dataset of patients obtained from the ED database of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital (Salerno, Italy) from the period 2014-2019. Results For the years considered, 496,172 admissions were evaluated and 143,641 of them (28.9%) revealed a prolonged ED-LOS. Considering the complete data (48.1% female vs. 51.9% male), 51.7% patients with prolonged ED-LOS were male and 47.3% were female. Regarding the age groups, the patients that were most affected by prolonged ED-LOS were over 64 years. The evaluation metrics of Random Forest algorithm proved to be the best; indeed, it achieved the highest accuracy (74.8%), precision (72.8%), and recall (74.8%) in predicting ED-LOS. Conclusions Different variables, referring to patients' personal and clinical attributes and to the ED process, have a direct impact on the value of ED-LOS. The suggested prediction model has encouraging results; thus, it may be applied to anticipate and manage ED-LOS, preventing crowding and optimising effectiveness and efficiency of the ED.
Collapse
Affiliation(s)
- Carlo Ricciardi
- Department of Electrical Engineering and Information Technology, University of Naples “Federico II”, Naples, Italy
| | | | - Teresa Angela Trunfio
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, Naples, Italy
| | - Massimo Majolo
- Department of Public Health, University of Naples “Federico II”, Naples, Italy
| | - Maria Romano
- Department of Electrical Engineering and Information Technology, University of Naples “Federico II”, Naples, Italy
| | - Francesco Amato
- Department of Electrical Engineering and Information Technology, University of Naples “Federico II”, Naples, Italy
| | - Giovanni Improta
- Department of Public Health, University of Naples “Federico II”, Naples, Italy
- Interdepartmental Center for Research in Healthcare Management and Innovation in Healthcare (CIRMIS), University of Naples “Federico II”, Naples, Italy
| |
Collapse
|
8
|
Brick R, Hekman DJ, Werner NE, Rodakowski J, Cadmus-Bertram L, Fields B. Health system and patient-level factors associated with multidisciplinary care and patient education among hospitalized, older cancer survivors. PEC INNOVATION 2023; 3:100192. [PMID: 37502427 PMCID: PMC10369477 DOI: 10.1016/j.pecinn.2023.100192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 07/12/2023] [Accepted: 07/14/2023] [Indexed: 07/29/2023]
Abstract
Objective The purpose of this study was to examine system- and patient-level factors associated with the number of healthcare disciplines involved in delivery of patient education among hospitalized older cancer survivors. Methods We used electronic health record (EHR) data from a single institution documenting patient education among hospitalized older patients (≥65 years) with a history of cancer between 9/1/2018 and 10/1/2019. We used parametric ordinal logistic regression to assess the number of healthcare disciplines involved in documented education activities. Results The sample (n = 446) was predominantly male, White, and on average 74 years old. Adjusting for patient and system-level variables, men and larger department units had higher odds of receiving education from fewer healthcare disciplines. Patients with a history of breast or prostate cancer and longer lenths of stay had lower odds of receiving patient education from fewer healthcare disciplines. Conclusion Hospital size, severity of illness, and cancer type are associated with delivery of multidisciplinary education in this sample. Innovation EHR provides an opportunity to identify patterns in patient education among cancer survivors. Future research should investigate provider perspectives of the findings to inform provider- and system-level strategies to improve patient education.
Collapse
Affiliation(s)
- Rachelle Brick
- Cancer Prevention Fellowship Program, Division of Cancer Prevention, National Cancer Institute, 9609 Medical Center Dr, Rockville, MD 20850, USA
| | - Daniel J. Hekman
- University of Wisconsin-Madison, Department of Emergency Medicine, 600 Highland Avenue Madison, WI 53792, USA
| | - Nicole E. Werner
- Indiana University, Department of Health & Wellness Design, 1025 E 7 St, Bloomington, IN 47405, USA
| | - Juleen Rodakowski
- University of Pittsburgh, Department of Occupational Therapy, Bridgeside Point I, 100 Technology Drive, Pittsburgh, PA 15219, USA
| | - Lisa Cadmus-Bertram
- University of Wisconsin-Madison, Department of Kinesiology, 2170 Medical Sciences Center, 1300 University Avenue, Madison, WI 53706, USA
| | - Beth Fields
- University of Wisconsin-Madison, Department of Kinesiology, 2170 Medical Sciences Center, 1300 University Avenue, Madison, WI 53706, USA
| |
Collapse
|
9
|
Moura A, Baliafa E, Alexandropoulos C, Papazoglou AS, Kartas A, Samaras A, Solovou C, Kontopyrgou D, Ioannou M, Moysidis DV, Bekiaridou A, Tzikas A, Ziakas A, Giannakoulas G. Association of Length of Stay With the Clinical Trajectory of Hospitalized Patients With Atrial Fibrillation: Staying Less Is More? Am J Cardiol 2023; 206:254-261. [PMID: 37716224 DOI: 10.1016/j.amjcard.2023.08.066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Accepted: 08/14/2023] [Indexed: 09/18/2023]
Abstract
Data predicting the length of stay (LOS) in patients with concurrent atrial fibrillation (AF) are scarce. This study aimed to investigate the potential predictors for prolonged LOS and its prognostic value. In this observational post hoc analysis of the MISOAC-AF (Motivational Interviewing to Support Oral AntiCoagulation adherence in patients with non-valvular Atrial Fibrillation) randomized trial logistic regression analyses were conducted to identify the parameters associated with prolonged LOS (defined as >7 days according to diagnostic accuracy analyses). Kaplan-Meier and Cox regression analyses were performed to generate survival curves and adjusted hazard ratios (aHRs) with 95% confidence intervals (CIs) for the primary end point of all-cause mortality and for the secondary end points during a median 3.7-year follow-up. Of the 1,057 patients studied, 462 (43.7%) were hospitalized for ≥7 days. Heart failure with reduced ejection fracture (aHR 1.75, 95% CI 1.17 to 2.63), permanent AF (aHR 1.72, 95% CI 1.29 to 2.31), history of coronary artery disease (aHR 2.32, 95% CI 1.59 to 3.39), and advanced or end-stage chronic kidney disease (aHR 1.54, 95% CI 1.15 to 2.06) were independently associated with prolonged hospitalization. Prolonged LOS was independently linked with increased all-cause mortality rates (aHR 1.68, 95% CI 1.25 to 2.26), cardiovascular mortality (aHR 1.92, 95% CI 1.36 to 2.72), major bleeding (aHR 3.07, 95% CI 1.07 to 8.78), and the composite outcome of cardiovascular death or rehospitalization (aHR 1.31, 95% CI 1.04 to 1.66). Each extra day of LOS was an independent predictor of all-cause mortality (aHR 1.03, 95% CI 1.02 to 1.04). Hospitalized patients with concurrent AF carry a substantial morbidity burden being prone to extended LOS. A jointed approach seems reasonable to reduce the LOS in patients with AF.
Collapse
Affiliation(s)
- Andreanna Moura
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Eleni Baliafa
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Christos Alexandropoulos
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | | | - Anastasios Kartas
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | | | - Chrysi Solovou
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Dimitra Kontopyrgou
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Maria Ioannou
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Dimitrios V Moysidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Alexandra Bekiaridou
- Elmezzi Graduate School of Molecular Medicine, Northwell Health, Manhasset, New York; Feinstein Institutes for Medical Research, Northwell Health, Manhasset, New York
| | - Apostolos Tzikas
- Second Department of Cardiology, Hippokrateion, Thessaloniki, Greece; Interbalkan European Medical Center, Thessaloniki, Greece
| | - Antonios Ziakas
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - George Giannakoulas
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, Thessaloniki, Greece.
| |
Collapse
|
10
|
Zeleke AJ, Palumbo P, Tubertini P, Miglio R, Chiari L. Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis. Front Artif Intell 2023; 6:1179226. [PMID: 37588696 PMCID: PMC10426288 DOI: 10.3389/frai.2023.1179226] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Accepted: 07/10/2023] [Indexed: 08/18/2023] Open
Abstract
Objective This study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework). Methods We analyzed a dataset of patients admitted through the ED to the "Sant"Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%). Results A total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6-7 day mean difference between actual and predicted LoS. Conclusion Our results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.
Collapse
Affiliation(s)
- Addisu Jember Zeleke
- Department of Electrical, Electronic, and Information Engineering Guglielmo Marconi, University of Bologna, Bologna, Italy
| | - Pierpaolo Palumbo
- Department of Electrical, Electronic, and Information Engineering Guglielmo Marconi, University of Bologna, Bologna, Italy
| | - Paolo Tubertini
- Enterprise Information Systems for Integrated Care and Research Data Management, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Azienda Ospedaliero—Universitaria di Bologna, Bologna, Italy
| | - Rossella Miglio
- Department of Statistical Sciences, University of Bologna, Bologna, Italy
| | - Lorenzo Chiari
- Department of Electrical, Electronic, and Information Engineering Guglielmo Marconi, University of Bologna, Bologna, Italy
- Health Sciences and Technologies Interdepartmental Center for Industrial Research (CIRI SDV), University of Bologna, Bologna, Italy
| |
Collapse
|
11
|
Amawi H, Arabyat RM, Al-Azzam S, AlZu'bi T, U'wais HT, Hammad AM, Amawi R, Nusair MB. The Length of Hospital Stay of Patients with Venous Thromboembolism: A Cross-Sectional Study from Jordan. MEDICINA (KAUNAS, LITHUANIA) 2023; 59:medicina59040727. [PMID: 37109685 PMCID: PMC10145113 DOI: 10.3390/medicina59040727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Revised: 03/21/2023] [Accepted: 03/29/2023] [Indexed: 04/29/2023]
Abstract
Background and Objectives: Venous thromboembolism is one of the leading causes of mortality and disability worldwide. Treatment with anticoagulation therapy is essential and requires a delicate approach to select the most appropriate option to improve patient outcomes, including the length of hospital stay (LOS). The aim of this study was to determine the LOS among patients with acute onset of VTE in several public hospitals in Jordan. Materials and Methods: In this study, we recruited hospitalized patients with a confirmed diagnosis of VTE. We reviewed the electronic medical records and charts of VTE admitted patients in addition to a detailed survey to collect the patients' self-reported data. Hospital LOS was categorized into three levels: 1-3 days, 4-6 days, and ≥7 days. An ordered logistic regression model was used to study the significant predictors of LOS. Results: A total of 317 VTE patients were recruited, with 52.4% of them were male and 35.3% aged between 50 and 69 years. Most patients had a deep vein thrombosis (DVT) diagnosis (84.2%), and most of the VTE cases were admitted for the first-time (64.6%). The majority of the patients were smokers (57.2%), overweight/obese (66.3%), and hypertensive (59%). Most of the VTE patients received Warfarin overlapped with low molecular weight heparins as their treatment regimen (>70%). Almost half of the admitted VTE patients (45%) were hospitalized for at least 7 days. Longer LOS was significantly associated with hypertension. Conclusions: We recommend using therapies that have been proven to reduce hospital LOS, such as non-vitamin K antagonist oral anticoagulants or direct oral anticoagulants, to treat VTE patients in Jordan. Additionally, preventing and controlling comorbidities such as hypertension is essential.
Collapse
Affiliation(s)
- Haneen Amawi
- Department of Pharmacy Practice and Clinical Pharmacy, Faculty of Pharmacy, Yarmouk University, Irbid 22110, Jordan
| | - Rasha M Arabyat
- Department of Pharmacy Practice and Clinical Pharmacy, Faculty of Pharmacy, Yarmouk University, Irbid 22110, Jordan
| | - Sayer Al-Azzam
- Department of Clinical Pharmacy, Faculty of Pharmacy, Jordan University of Science and Technology, Irbid 22110, Jordan
| | - Toqa AlZu'bi
- Department of Clinical Pharmacy, Faculty of Pharmacy, Jordan University of Science and Technology, Irbid 22110, Jordan
| | - Hamza Tayseer U'wais
- Department of Pharmacy Practice and Clinical Pharmacy, Faculty of Pharmacy, Yarmouk University, Irbid 22110, Jordan
| | - Alaa M Hammad
- Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman 11733, Jordan
| | - Ruba Amawi
- The Ministry of Health, Amman 11118, Jordan
| | - Mohammad B Nusair
- Department of Pharmacy Practice and Clinical Pharmacy, Faculty of Pharmacy, Yarmouk University, Irbid 22110, Jordan
- Department of Sociobehavioral and Administrative Pharmacy, College of Pharmacy, Nova Southeastern University, Fort Lauderdale, FL 33328, USA
| |
Collapse
|
12
|
Chen R, Zhang S, Li J, Guo D, Zhang W, Wang X, Tian D, Qu Z, Wang X. A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm. BMC Med Inform Decis Mak 2023; 23:49. [PMID: 36949434 PMCID: PMC10031936 DOI: 10.1186/s12911-023-02140-4] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2021] [Accepted: 03/02/2023] [Indexed: 03/24/2023] Open
Abstract
BACKGROUND The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess the efficiency of hospital management and patient quality of care. This study established a prediction model based on a machine learning algorithm to predict ischemic stroke patients' LOS. METHODS A total of 18,195 ischemic stroke patients' electronic medical records and 28 attributes were extracted from electronic medical records in a large comprehensive hospital in China. The prediction of LOS was regarded as a multi classification problem, and LOS was divided into three categories: 1-7 days, 8-14 days and more than 14 days. After preprocessing the data and feature selection, the XGBoost algorithm was used to build a machine learning model. Ten fold cross-validation was used for model validation. The accuracy (ACC), recall rate (RE) and F1 measure were used to evaluate the performance of the prediction model of LOS of ischemic stroke patients. Finally, the XGBoost algorithm was used to identify and remove irrelevant features by ranking all attributes based on feature importance. RESULTS Compared with the naive Bayesian algorithm, logistic region algorithm, decision tree classifier algorithm and ADaBoost classifier algorithm, the XGBoot algorithm has higher ACC, RE and F1 measure. The average ACC, RE and F1 measure were 0.89, 0.89 and 0.89 under the 10-fold cross-validation. According to the analysis of the importance of features, the LOS of ischemic stroke patients was affected by demographic characteristics, past medical history, admission examination features, and operation characteristics. Finally, the features in terms of hemiplegia aphasia, MRS, NIHSS, TIA, Operation or not, coma index etc. were found to be the top features in importance in predicting the LOS of ischemic stroke patients. CONCLUSIONS The XGBoost algorithm was an appropriate machine learning method for predicting the LOS of patients with ischemic stroke. Based on the prediction model, an intelligent medical management prediction system could be developed to predict the LOS based on ischemic stroke patients' electronic medical records.
Collapse
Affiliation(s)
- Rui Chen
- Refined Management Office, Cangzhou Central Hospital, Cangzhou, China
| | - Shengfa Zhang
- National Population Heath Data Center, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| | - Jie Li
- School of Economics and Management, Hebei University of Technology, Tianjin, China
| | - Dongwei Guo
- School of Economics and Management, Hebei University of Technology, Tianjin, China
| | - Weijun Zhang
- School of Social Development and Public Policy, Beijing Normal University, Beijing, China
| | - Xiaoying Wang
- School of Social Development and Public Policy, Beijing Normal University, Beijing, China
| | - Donghua Tian
- School of Social Development and Public Policy, Beijing Normal University, Beijing, China
| | - Zhiyong Qu
- School of Social Development and Public Policy, Beijing Normal University, Beijing, China
| | - Xiaohua Wang
- School of Social Development and Public Policy, Beijing Normal University, Beijing, China
| |
Collapse
|
13
|
Zou H, Yang W, Wang M, Zhu Q, Liang H, Wu H, Tang L. Predicting length of stay ranges by using novel deep neural networks. Heliyon 2023; 9:e13573. [PMID: 36852025 PMCID: PMC9958433 DOI: 10.1016/j.heliyon.2023.e13573] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Revised: 01/31/2023] [Accepted: 02/02/2023] [Indexed: 02/11/2023] Open
Abstract
Background and aims Accurately predicting length of stay (LOS) is considered a challenging task for health care systems globally. In previous studies on LOS range prediction, researchers commonly pre-classified the LOS ranges, which were the same for all patients in the same classification, and then utilized a classifier for prediction. In this study, we innovatively aimed to predict the specific LOS range for each patient (the LOS range was different for each patient). Methods In the modified deep neural network (DNN), the overall sample error (root mean square error (RMSE) method), the estimated sample error (ERRpred method), the probability distribution with different loss functions (Dispred_Loss1, Dispred_Loss2, and Dispred_Loss3 method), and the generative adversarial networks (WGAN-GP for LOS method) are used for LOS range prediction. The Medical Information Mart for Intensive Care III (MIMIC-III) database is used to validate these methods. Results The RMSE method is convenient for LOS range prediction, but the predicted ranges are all consistent in the same batch of samples. The ERRpred method can achieve better prediction results in samples with low errors. However, the prediction effect is worse in samples with larger errors. The Dispred_Loss1 method encounters a training instability problem. The Dispred_Loss2 and Dispred_Loss3 methods perform well in making predictions. Although WGAN-GP for LOS method does not show a substantial advantage over other methods, this method might have the potential to improve the predictive performance. Conclusion The results show that it is possible to achieve an acceptable accurate LOS range prediction through a reasonable model design, which may help physicians in the clinic.
Collapse
Affiliation(s)
- Hong Zou
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China.,Department of Liver Surgery & Liver Transplantation, State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University and Collaborative Innovation Center of Biotherapy, Chengdu 610044, Sichuan Province, China
| | - Wei Yang
- Department of Urology, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Meng Wang
- Department of Traditional Chinese Medicine, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Qiao Zhu
- Department of Obstetrics and Gynecology, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Hongyin Liang
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Hong Wu
- Department of Liver Surgery & Liver Transplantation, State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University and Collaborative Innovation Center of Biotherapy, Chengdu 610044, Sichuan Province, China
| | - Lijun Tang
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| |
Collapse
|
14
|
Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm. JOURNAL OF HEALTHCARE ENGINEERING 2023; 2023:9673395. [PMID: 36824405 PMCID: PMC9943622 DOI: 10.1155/2023/9673395] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/17/2022] [Revised: 12/01/2022] [Accepted: 01/17/2023] [Indexed: 02/16/2023]
Abstract
The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.
Collapse
|
15
|
Analysis of length of stay for patients admitted to Korean hospitals based on the Korean National Health Insurance Service Database. INFORMATICS IN MEDICINE UNLOCKED 2023. [DOI: 10.1016/j.imu.2023.101178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023] Open
|
16
|
Orooji A, Shanbehzadeh M, Mirbagheri E, Kazemi-Arpanahi H. Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19. BMC Infect Dis 2022; 22:923. [PMID: 36494613 PMCID: PMC9733380 DOI: 10.1186/s12879-022-07921-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2021] [Accepted: 12/06/2022] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND The exponential spread of coronavirus disease 2019 (COVID-19) causes unexpected economic burdens to worldwide health systems with severe shortages in hospital resources (beds, staff, equipment). Managing patients' length of stay (LOS) to optimize clinical care and utilization of hospital resources is very challenging. Projecting the future demand requires reliable prediction of patients' LOS, which can be beneficial for taking appropriate actions. Therefore, the purpose of this research is to develop and validate models using a multilayer perceptron-artificial neural network (MLP-ANN) algorithm based on the best training algorithm for predicting COVID-19 patients' hospital LOS. METHODS Using a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020 to December 20, 2020 were analyzed. In this study, first, the correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at a P-value < 0.2 were used in model construction. Then, the prediction models were developed based on 12 training algorithms according to full and selected feature datasets (90% of the training, with 10% used for model validation). Afterward, the root mean square error (RMSE) was used to assess the models' performance in order to select the best ANN training algorithm. Finally, a total of 343 patients were used for the external validation of the models. RESULTS After implementing feature selection, a total of 20 variables were determined as the contributing factors to COVID-19 patients' LOS in order to build the models. The conducted experiments indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian regularization (BR) training algorithm for whole and selected features with an RMSE of 1.6213 and 2.2332, respectively. CONCLUSIONS MLP-ANN-based models can reliably predict LOS in hospitalized patients with COVID-19 using readily available data at the time of admission. In this regard, the models developed in our study can help health systems to optimally allocate limited hospital resources and make informed evidence-based decisions.
Collapse
Affiliation(s)
- Azam Orooji
- grid.464653.60000 0004 0459 3173Department of Medical Informatics, Department of Advanced Technologies, School of Medicine, North Khorasan University of Medical Science (NKUMS), North Khorasan, Iran
| | - Mostafa Shanbehzadeh
- grid.449129.30000 0004 0611 9408Department of Health Information Management, Department of Health Information Technology, School of Paramedical, Ilam University of Medical Sciences, Ilam, Iran
| | - Esmat Mirbagheri
- grid.411746.10000 0004 4911 7066Department of Health Information Management, Iran University of Medical Sciences, Tehran, Iran
| | - Hadi Kazemi-Arpanahi
- Department of Health Information Management, Department of Health Information Technology, Abadan University of Medical Sciences, Abadan, Iran , Department of Health Information Management, Student Research Committee, Abadan University of Medical Sciences, Abadan, Iran
| |
Collapse
|
17
|
Temporal convolutional networks and data rebalancing for clinical length of stay and mortality prediction. Sci Rep 2022; 12:21247. [PMID: 36481828 PMCID: PMC9732283 DOI: 10.1038/s41598-022-25472-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Accepted: 11/30/2022] [Indexed: 12/13/2022] Open
Abstract
It is critical for hospitals to accurately predict patient length of stay (LOS) and mortality in real-time. We evaluate temporal convolutional networks (TCNs) and data rebalancing methods to predict LOS and mortality. This is a retrospective cohort study utilizing the MIMIC-III database. The MIMIC-Extract pipeline processes 24 hour time-series clinical objective data for 23,944 unique patient records. TCN performance is compared to both baseline and state-of-the-art machine learning models including logistic regression, random forest, gated recurrent unit with decay (GRU-D). Models are evaluated for binary classification tasks (LOS > 3 days, LOS > 7 days, mortality in-hospital, and mortality in-ICU) with and without data rebalancing and analyzed for clinical runtime feasibility. Data is split temporally, and evaluations utilize tenfold cross-validation (stratified splits) followed by simulated prospective hold-out validation. In mortality tasks, TCN outperforms baselines in 6 of 8 metrics (area under receiver operating characteristic, area under precision-recall curve (AUPRC), and F-1 measure for in-hospital mortality; AUPRC, accuracy, and F-1 for in-ICU mortality). In LOS tasks, TCN performs competitively to the GRU-D (best in 6 of 8) and the random forest model (best in 2 of 8). Rebalancing improves predictive power across multiple methods and outcome ratios. The TCN offers strong performance in mortality classification and offers improved computational efficiency on GPU-enabled systems over popular RNN architectures. Dataset rebalancing can improve model predictive power in imbalanced learning. We conclude that temporal convolutional networks should be included in model searches for critical care outcome prediction systems.
Collapse
|
18
|
Multilayer dynamic ensemble model for intensive care unit mortality prediction of neonate patients. J Biomed Inform 2022; 135:104216. [DOI: 10.1016/j.jbi.2022.104216] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2021] [Revised: 09/25/2022] [Accepted: 09/28/2022] [Indexed: 12/26/2022]
|
19
|
Length of Hospitalization-Related Differences and Associated Long-Term Prognosis of Patients with Cardiac Resynchronization Therapy: A Propensity Score-Matched Cohort. J Cardiovasc Dev Dis 2022; 9:jcdd9100354. [PMID: 36286306 PMCID: PMC9604508 DOI: 10.3390/jcdd9100354] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2022] [Revised: 09/27/2022] [Accepted: 09/30/2022] [Indexed: 11/11/2022] Open
Abstract
Previous studies indicated that prolonged lengths of hospitalization (LOH) during cardiac resynchronization therapy (CRT) implantation are associated with poorer physical status and higher in-hospital mortality. However, evidence on the impact of LOH on the long-term prognosis of CRT patients is limited. The purpose of this study was to assess LOH-related prognostic differences in CRT patients. In the propensity score-matched cohort, patients with standard LOH (≤7 days, n = 172) were compared with those with prolonged LOH (>7 days, n = 172) for cardiac function and study outcomes during follow-up. The study outcomes were all-cause death and heart failure (HF) hospitalization. In addition, cardiac function and changes in cardiac function at the follow-up period were used for comparison. At a mean follow-up of 3.36 years, patients with prolonged LOH, as compared with those with standard LOH, were associated with a significantly higher risk of all-cause death (hazard ratio [HR] 1.87, 95% confidence interval [CI] 1.18−2.96, p = 0.007), and a higher risk of HF hospitalization (HR 1.68, 95% CI 1.08−2.63, p = 0.023). Moreover, patients with standard LOH had a more significant improvement in cardiac function and a pronounced reduction in QRS duration during follow-up than those with prolonged LOH. LOH-associated differences were found in the long-term prognosis of CRT patients. Patients with prolonged LOH had a worse prognosis than those with standard LOH.
Collapse
|
20
|
Implementation of Predictive Algorithms for the Study of the Endarterectomy LOS. Bioengineering (Basel) 2022; 9:bioengineering9100546. [PMID: 36290514 PMCID: PMC9598220 DOI: 10.3390/bioengineering9100546] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Revised: 10/04/2022] [Accepted: 10/07/2022] [Indexed: 11/26/2022] Open
Abstract
Background: In recent years, the length of hospital stay (LOS) following endarterectomy has decreased significantly from 4 days to 1 day. LOS is influenced by several common complications and factors that can adversely affect the patient’s health and may vary from one healthcare facility to another. The aim of this work is to develop a forecasting model of the LOS value to investigate the main factors affecting LOS in order to save healthcare cost and improve management. Methods: We used different regression and machine learning models to predict the LOS value based on the clinical and organizational data of patients undergoing endarterectomy. Data were obtained from the discharge forms of the “San Giovanni di Dio e Ruggi d’Aragona” University Hospital (Salerno, Italy). R2 goodness of fit and the results in terms of accuracy, precision, recall and F1-score were used to compare the performance of various algorithms. Results: Before implementing the models, the preliminary correlation study showed that LOS was more dependent on the type of endarterectomy performed. Among the regression algorithms, the best was the multiple linear regression model with an R2 value of 0.854, while among the classification algorithms for LOS divided into classes, the best was decision tree, with an accuracy of 80%. The best performance was obtained in the third class, which identifies patients with prolonged LOS, with a precision of 95%. Among the independent variables, the most influential on LOS was type of endarterectomy, followed by diabetes and kidney disorders. Conclusion: The resulting forecast model demonstrates its effectiveness in predicting the value of LOS that could be used to improve the endarterectomy surgery planning.
Collapse
|
21
|
Verma A, Sanaiha Y, Hadaya J, Maltagliati AJ, Tran Z, Ramezani R, Shemin RJ, Benharash P, Benharash P, Shemin RJ, Satou N, Nguyen T, Clary C, Madani M, Higgins J, Steltzner D, Kiaii B, Young JN, Behan K, Houston H, Matsumoto C, Sun JC, Flavin L, Fopiano P, Cabrera M, Khaki R, Washabaugh P. Parsimonious machine learning models to predict resource use in cardiac surgery across a statewide collaborative. JTCVS OPEN 2022; 11:214-228. [PMID: 36172420 PMCID: PMC9510828 DOI: 10.1016/j.xjon.2022.04.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 02/18/2022] [Accepted: 04/12/2022] [Indexed: 11/03/2022]
Abstract
Objective Methods Results Conclusions
Collapse
|
22
|
Length of Stay Prediction Model of Indoor Patients Based on Light Gradient Boosting Machine. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:9517029. [PMID: 36082346 PMCID: PMC9448550 DOI: 10.1155/2022/9517029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 07/31/2022] [Accepted: 08/10/2022] [Indexed: 11/17/2022]
Abstract
The influx of hospital patients has become common in recent years. Hospital management departments need to redeploy healthcare resources to meet the massive medical needs of patients. In this process, the hospital length of stay (LOS) of different patients is a crucial reference to the management department. Therefore, building a model to predict LOS is of great significance. Five machine learning (ML) algorithms named Lasso regression (LR), ridge regression (RR), random forest regression (RFR), light gradient boosting machine (LightGBM), and extreme gradient boosting regression (XGBR) and six feature encoding methods named label encoding, count encoding, one-hot encoding, target encoding, leave-one-out encoding, and the proposed encoding method are used to construct the regression prediction model. The Scikit-Learn toolbox on the Python platform builds the prediction model. The input is the dataset named Hospital Inpatient Discharges (SPARCS De-Identified) 2017 with 2343569 instances provided by the New York State Department of Health verify the model after removing 2.2% of the missing data, and the model ultimately uses mean squared error (MSE) and coefficient of determination (R2) as the performance measurement. The results show that the model with the LightGBM algorithm and the proposed encoding method has the best R2 (96.0%) and MSE score (2.231).
Collapse
|
23
|
Ayad A, Hallawa A, Peine A, Martin L, Fazlic LB, Dartmann G, Marx G, Schmeink A. Predicting Abnormalities in Laboratory Values of Patients in the Intensive Care Unit Using Different Deep Learning Models: Comparative Study. JMIR Med Inform 2022; 10:e37658. [PMID: 36001363 PMCID: PMC9453586 DOI: 10.2196/37658] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Revised: 06/05/2022] [Accepted: 06/12/2022] [Indexed: 11/13/2022] Open
Abstract
Background In recent years, the volume of medical knowledge and health data has increased rapidly. For example, the increased availability of electronic health records (EHRs) provides accurate, up-to-date, and complete information about patients at the point of care and enables medical staff to have quick access to patient records for more coordinated and efficient care. With this increase in knowledge, the complexity of accurate, evidence-based medicine tends to grow all the time. Health care workers must deal with an increasing amount of data and documentation. Meanwhile, relevant patient data are frequently overshadowed by a layer of less relevant data, causing medical staff to often miss important values or abnormal trends and their importance to the progression of the patient’s case. Objective The goal of this work is to analyze the current laboratory results for patients in the intensive care unit (ICU) and classify which of these lab values could be abnormal the next time the test is done. Detecting near-future abnormalities can be useful to support clinicians in their decision-making process in the ICU by drawing their attention to the important values and focus on future lab testing, saving them both time and money. Additionally, it will give doctors more time to spend with patients, rather than skimming through a long list of lab values. Methods We used Structured Query Language to extract 25 lab values for mechanically ventilated patients in the ICU from the MIMIC-III and eICU data sets. Additionally, we applied time-windowed sampling and holding, and a support vector machine to fill in the missing values in the sparse time series, as well as the Tukey range to detect and delete anomalies. Then, we used the data to train 4 deep learning models for time series classification, as well as a gradient boosting–based algorithm and compared their performance on both data sets. Results The models tested in this work (deep neural networks and gradient boosting), combined with the preprocessing pipeline, achieved an accuracy of at least 80% on the multilabel classification task. Moreover, the model based on the multiple convolutional neural network outperformed the other algorithms on both data sets, with the accuracy exceeding 89%. Conclusions In this work, we show that using machine learning and deep neural networks to predict near-future abnormalities in lab values can achieve satisfactory results. Our system was trained, validated, and tested on 2 well-known data sets to ensure that our system bridged the reality gap as much as possible. Finally, the model can be used in combination with our preprocessing pipeline on real-life EHRs to improve patients’ diagnosis and treatment.
Collapse
Affiliation(s)
- Ahmad Ayad
- Chair of Information Theory and Data Analytics, Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| | - Ahmed Hallawa
- Department of Intensive Care and Intermediate Care, University Hospital Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| | - Arne Peine
- Department of Intensive Care and Intermediate Care, University Hospital Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| | - Lukas Martin
- Department of Intensive Care and Intermediate Care, University Hospital Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| | - Lejla Begic Fazlic
- Fachbereich Umweltplanung/Umwelttechnik - Fachrichtung Informatik, Trier University of Applied Sciences, Trier, Germany
| | - Guido Dartmann
- Fachbereich Umweltplanung/Umwelttechnik - Fachrichtung Informatik, Trier University of Applied Sciences, Trier, Germany
| | - Gernot Marx
- Department of Intensive Care and Intermediate Care, University Hospital Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| | - Anke Schmeink
- Chair of Information Theory and Data Analytics, Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany
| |
Collapse
|
24
|
Quazi S. Artificial intelligence and machine learning in precision and genomic medicine. Med Oncol 2022; 39:120. [PMID: 35704152 PMCID: PMC9198206 DOI: 10.1007/s12032-022-01711-1] [Citation(s) in RCA: 45] [Impact Index Per Article: 22.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Accepted: 03/14/2022] [Indexed: 10/28/2022]
Abstract
The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.
Collapse
Affiliation(s)
- Sameer Quazi
- GenLab Biosolutions Private Limited, Bangalore, Karnataka, 560043, India.
- Department of Biomedical Sciences, School of Life Sciences, Anglia Ruskin University, Cambridge, UK.
| |
Collapse
|
25
|
Abstract
The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.
Collapse
Affiliation(s)
- Sameer Quazi
- GenLab Biosolutions Private Limited, Bangalore, Karnataka, 560043, India.
- Department of Biomedical Sciences, School of Life Sciences, Anglia Ruskin University, Cambridge, UK.
| |
Collapse
|
26
|
Czapla M, Juárez-Vela R, Łokieć K, Wleklik M, Karniej P, Smereka J. The Association between Nutritional Status and Length of Hospital Stay among Patients with Hypertension. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19105827. [PMID: 35627363 PMCID: PMC9140333 DOI: 10.3390/ijerph19105827] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 03/19/2022] [Revised: 05/06/2022] [Accepted: 05/08/2022] [Indexed: 02/06/2023]
Abstract
Background: Nutritional status is related to the prognosis and length of hospital stay (LOS) of patients with hypertension (HT). This study aimed to assess how nutritional status and body mass index (BMI) affect LOS for patients with hypertension. Method: We performed a retrospective analysis of 586 medical records of patients who had been admitted to the Institute of Heart Diseases of the University Clinical Hospital in Wroclaw, Poland. Results: A total of 586 individuals were included in the analysis. Individuals who were at a nutritional risk represented less than 2% of the study population, but more than 60% were overweight or obese. The mean BMI was 28.4 kg/m2 (SD: 5.16). LOS averaged 3.53 days (SD = 2.78). In the case of obese individuals, hospitalisation lasted for 3.4 ± 2.43 days, which was significantly longer than for patients of normal weight. For underweight patients, hospitalisation lasted for 5.14 ± 2.27 days, which was also significantly longer than for those in other BMI categories (p = 0.017). The independent predictors of shorter hospitalisations involved higher LDL concentration (parameter of regression: −0.015) and HDL concentration (parameter of regression: −0.04). Conclusions: The study revealed that with regard to the nutritional status of hypertensive patients, being either underweight or obese was associated with longer LOS. Additional factors that related to prolonged LOS were lower LDL and HDL levels and higher CRP concentrations.
Collapse
Affiliation(s)
- Michał Czapla
- Laboratory for Experimental Medicine and Innovative Technologies, Department of Emergency Medical Service, Wroclaw Medical University, 51-616 Wroclaw, Poland; (M.C.); (J.S.)
- Institute of Heart Diseases, University Hospital, 50-566 Wroclaw, Poland
- Group of Research in Care (GRUPAC), Faculty of Nursing, University of La Rioja, 26006 Logroño, Spain;
| | - Raúl Juárez-Vela
- Group of Research in Care (GRUPAC), Faculty of Nursing, University of La Rioja, 26006 Logroño, Spain;
- Correspondence:
| | - Katarzyna Łokieć
- Department of Propaedeutic of Civilization Diseases, Medical University of Lodz, 90-251 Lodz, Poland;
| | - Marta Wleklik
- Department of Nursing and Obstetrics, Faculty of Health Sciences, Wroclaw Medical University, 51-618 Wroclaw, Poland;
| | - Piotr Karniej
- Group of Research in Care (GRUPAC), Faculty of Nursing, University of La Rioja, 26006 Logroño, Spain;
- Faculty of Finance and Management, WSB University in Wrocław, 53-609 Wroclaw, Poland
| | - Jacek Smereka
- Laboratory for Experimental Medicine and Innovative Technologies, Department of Emergency Medical Service, Wroclaw Medical University, 51-616 Wroclaw, Poland; (M.C.); (J.S.)
| |
Collapse
|
27
|
Fan G, Yang S, Liu H, Xu N, Chen Y, He J, Su X, Pang M, Liu B, Han L, Rong L. Machine Learning-based Prediction of Prolonged Intensive Care Unit Stay for Critical Patients with Spinal Cord Injury. Spine (Phila Pa 1976) 2022; 47:E390-E398. [PMID: 34690328 DOI: 10.1097/brs.0000000000004267] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
STUDY DESIGN A retrospective cohort study. OBJECTIVE The objective of the study was to develop machine-learning (ML) classifiers for predicting prolonged intensive care unit (ICU)-stay and prolonged hospital-stay for critical patients with spinal cord injury (SCI). SUMMARY OF BACKGROUND DATA Critical patients with SCI in ICU need more attention. SCI patients with prolonged stay in ICU usually occupy vast medical resources and hinder the rehabilitation deployment. METHODS A total of 1599 critical patients with SCI were included in the study and labeled with prolonged stay or normal stay. All data were extracted from the eICU Collaborative Research Database and the Medical Information Mart for Intensive Care III-IV Database. The extracted data were randomly divided into training, validation and testing (6:2:2) subdatasets. A total of 91 initial ML classifiers were developed, and the top three initial classifiers with the best performance were further stacked into an ensemble classifier with logistic regressor. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicting outcome was prolonged ICU-stay, while the secondary predicting outcome was prolonged hospital-stay. RESULTS In predicting prolonged ICU-stay, the AUC of the ensemble classifier was 0.864 ± 0.021 in the three-time five-fold cross-validation and 0.802 in the independent testing. In predicting prolonged hospital-stay, the AUC of the ensemble classifier was 0.815 ± 0.037 in the three-time five-fold cross-validation and 0.799 in the independent testing. Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top three initial classifiers varied a lot in either predicting prolonged ICU-stay or discriminating prolonged hospital-stay. CONCLUSION The ensemble classifiers successfully predict the prolonged ICU-stay and the prolonged hospital-stay, which showed a high potential of assisting physicians in managing SCI patients in ICU and make full use of medical resources.Level of Evidence: 3.
Collapse
Affiliation(s)
- Guoxin Fan
- Department of Spine Surgery, Third Affiliated Hospital, Sun Yatsen University, Guangzhou, China
- Intelligent and Digital Surgery Innovation Center, Southern University of Science and Technology Hospital, Shenzhen, Guangdong, China
| | - Sheng Yang
- Department of Orthopedics, Shanghai Tenth People's Hospital, Tongji University School of Medicine, Shanghai, China
| | - Huaqing Liu
- Artificial Intelligence Innovation Center, Research Institute of Tsinghua, Pearl River Delta, Guangzhou, China
| | - Ningze Xu
- Tongji University School of Medicine, Shanghai, P. R. China
| | - Yuyong Chen
- Department of Spine Surgery, Third Affiliated Hospital, Sun Yatsen University, Guangzhou, China
- Intelligent and Digital Surgery Innovation Center, Southern University of Science and Technology Hospital, Shenzhen, Guangdong, China
| | - Jie He
- Intelligent and Digital Surgery Innovation Center, Southern University of Science and Technology Hospital, Shenzhen, Guangdong, China
| | - Xiuyun Su
- Intelligent and Digital Surgery Innovation Center, Southern University of Science and Technology Hospital, Shenzhen, Guangdong, China
| | - Mao Pang
- Department of Spine Surgery, Third Affiliated Hospital, Sun Yatsen University, Guangzhou, China
| | - Bin Liu
- Department of Spine Surgery, Third Affiliated Hospital, Sun Yatsen University, Guangzhou, China
| | - Lanqing Han
- Artificial Intelligence Innovation Center, Research Institute of Tsinghua, Pearl River Delta, Guangzhou, China
| | - Limin Rong
- Department of Spine Surgery, Third Affiliated Hospital, Sun Yatsen University, Guangzhou, China
| |
Collapse
|
28
|
Hu Z, Qiu H, Wang L, Shen M. Network analytics and machine learning for predicting length of stay in elderly patients with chronic diseases at point of admission. BMC Med Inform Decis Mak 2022; 22:62. [PMID: 35272654 PMCID: PMC8915508 DOI: 10.1186/s12911-022-01802-z] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Accepted: 03/07/2022] [Indexed: 11/13/2022] Open
Abstract
Background An aging population with a burden of chronic diseases puts increasing pressure on health care systems. Early prediction of the hospital length of stay (LOS) can be useful in optimizing the allocation of medical resources, and improving healthcare quality. However, the data available at the point of admission (PoA) are limited, making it difficult to forecast the LOS accurately. Methods In this study, we proposed a novel approach combining network analytics and machine learning to predict the LOS in elderly patients with chronic diseases at the PoA. Two networks, including multimorbidity network (MN) and patient similarity network (PSN), were constructed and novel network features were created. Five machine learning models (eXtreme Gradient Boosting, Gradient Boosting Decision Tree, Random Forest, Linear Support Vector Machine, and Deep Neural Network) with different input feature sets were developed to compare their performance. Results The experimental results indicated that the network features can bring significant improvements to the performances of the prediction models, suggesting that the MN and PSN are useful for LOS predictions. Conclusion Our predictive framework which integrates network science with data mining can forecast the LOS effectively at the PoA and provide decision support for hospital managers, which highlights the potential value of network-based machine learning in healthcare field.
Collapse
Affiliation(s)
- Zhixu Hu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, West Hi-Tech Zone, 611731, Chengdu, Sichuan, People's Republic of China
| | - Hang Qiu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, West Hi-Tech Zone, 611731, Chengdu, Sichuan, People's Republic of China. .,Big Data Research Center, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.
| | - Liya Wang
- Big Data Research Center, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Minghui Shen
- Health Information Center of Sichuan Province, Chengdu, People's Republic of China
| |
Collapse
|
29
|
Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods. MACHINE LEARNING WITH APPLICATIONS 2022. [DOI: 10.1016/j.mlwa.2021.100200] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022] Open
|
30
|
Ahmad M, Qurneh A, Saleh M, Aladaileh M, Alhamad R. The effect of implementing adult trauma clinical practice guidelines on outcomes of trauma patients and healthcare providers. Int Emerg Nurs 2022; 61:101143. [DOI: 10.1016/j.ienj.2021.101143] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2021] [Revised: 12/16/2021] [Accepted: 12/29/2021] [Indexed: 11/05/2022]
|
31
|
Kadri F, Dairi A, Harrou F, Sun Y. Towards accurate prediction of patient length of stay at emergency department: a GAN-driven deep learning framework. JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2022; 14:1-15. [PMID: 35132336 PMCID: PMC8810344 DOI: 10.1007/s12652-022-03717-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/27/2021] [Accepted: 01/11/2022] [Indexed: 05/28/2023]
Abstract
Recently, the hospital systems face a high influx of patients generated by several events, such as seasonal flows or health crises related to epidemics (e.g., COVID'19). Despite the extent of the care demands, hospital establishments, particularly emergency departments (EDs), must admit patients for medical treatments. However, the high patient influx often increases patients' length of stay (LOS) and leads to overcrowding problems within the EDs. To mitigate this issue, hospital managers need to predict the patient's LOS, which is an essential indicator for assessing ED overcrowding and the use of the medical resources (allocation, planning, utilization rates). Thus, accurately predicting LOS is necessary to improve ED management. This paper proposes a deep learning-driven approach for predicting the patient LOS in ED using a generative adversarial network (GAN) model. The GAN-driven approach flexibly learns relevant information from linear and nonlinear processes without prior assumptions on data distribution and significantly enhances the prediction accuracy. Furthermore, we classified the predicted patients' LOS according to time spent at the pediatric emergency department (PED) to further help decision-making and prevent overcrowding. The experiments were conducted on actual data obtained from the PED in Lille regional hospital center, France. The GAN model results were compared with other deep learning models, including deep belief networks, convolutional neural network, stacked auto-encoder, and four machine learning models, namely support vector regression, random forests, adaboost, and decision tree. Results testify that deep learning models are suitable for predicting patient LOS and highlight GAN's superior performance than the other models.
Collapse
Affiliation(s)
- Farid Kadri
- Aeroline DATA & CET, Agence 1031, Sopra Steria Group, Colomiers, 31770 France
| | - Abdelkader Dairi
- Laboratoire des Technologies de l’Environnement (LTE), BP 1523, Al M’naouar, 10587 Oran, Algeria
- University of Science and Technology of Oran-Mohamed Boudiaf, USTO-MB, BP 1505, El Mnaouar, Bir El Djir, 10587 Oran, Algeria
| | - Fouzi Harrou
- Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900 Saudi Arabia
| | - Ying Sun
- Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900 Saudi Arabia
| |
Collapse
|
32
|
Pičulin M, Smole T, Žunkovič B, Kokalj E, Robnik-Šikonja M, Kukar M, Fotiadis DI, Pezoulas VC, Tachos NS, Barlocco F, Mazzarotto F, Popović D, Maier LS, Velicki L, Olivotto I, MacGowan GA, Jakovljević DG, Filipović N, Bosnić Z. Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning. JMIR Med Inform 2022; 10:e30483. [PMID: 35107432 PMCID: PMC8851344 DOI: 10.2196/30483] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Revised: 10/27/2021] [Accepted: 12/04/2021] [Indexed: 01/15/2023] Open
Abstract
BACKGROUND Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). OBJECTIVE Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. METHODS The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. RESULTS The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. CONCLUSIONS By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.
Collapse
Affiliation(s)
- Matej Pičulin
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Tim Smole
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Bojan Žunkovič
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Enja Kokalj
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Marko Robnik-Šikonja
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Matjaž Kukar
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| | - Dimitrios I Fotiadis
- Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, Greece
| | - Vasileios C Pezoulas
- Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, Greece
| | - Nikolaos S Tachos
- Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, Greece
| | - Fausto Barlocco
- Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.,Cardiomyopathy Unit, Careggi University Hospital, University of Florence, Florence, Italy
| | - Francesco Mazzarotto
- Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.,Cardiomyopathy Unit, Careggi University Hospital, University of Florence, Florence, Italy.,National Heart and Lung Institute, Imperial College London, London, United Kingdom
| | - Dejana Popović
- Clinic for Cardiology, Clinical Center of Serbia, University of Belgrade, Belgrade, Serbia
| | - Lars S Maier
- Department of Internal Medicine II (Cardiology, Pneumology, Intensive Care Medicine), University Hospital Regensburg, Regensburg, Germany
| | - Lazar Velicki
- Faculty of Medicine, University of Novi Sad, Novi Sad, Serbia.,Institute of Cardiovascular Diseases Vojvodina, Sremska Kamenica, Serbia
| | - Iacopo Olivotto
- Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.,Cardiomyopathy Unit, Careggi University Hospital, University of Florence, Florence, Italy
| | - Guy A MacGowan
- Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, United Kingdom
| | - Djordje G Jakovljević
- Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, United Kingdom.,Faculty of Health and Life Sciences, Coventry University, Coventry, United Kingdom
| | - Nenad Filipović
- Bioengineering Research and Development Center, Kragujevac, Serbia
| | - Zoran Bosnić
- Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
| |
Collapse
|
33
|
Abbas A, Mosseri J, Lex JR, Toor J, Ravi B, Khalil EB, Whyne C. Machine learning using preoperative patient factors can predict duration of surgery and length of stay for total knee arthroplasty. Int J Med Inform 2022; 158:104670. [PMID: 34971918 DOI: 10.1016/j.ijmedinf.2021.104670] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2021] [Revised: 11/29/2021] [Accepted: 12/16/2021] [Indexed: 01/25/2023]
Abstract
BACKGROUND Total knee arthroplasty (TKA) is one of the most resource-intensive, high-volume surgical procedures. Two drivers of the cost of TKAs are duration of surgery (DOS) and postoperative inpatient length of stay (LOS). The ability to predict TKA DOS and LOS has substantial implications for hospital finances, scheduling, and resource allocation. The goal of this study was to predict DOS and LOS for elective unilateral TKAs using machine learning models (MLMs) based on preoperative factors. METHODS The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for unilateral TKAs from 2014 to 2019. The dataset was split into training, validation, and testing based on year. Models (linear, tree-based, and multilayer perceptron (MLP)) were fitted to the training set in scikit-learn and PyTorch, with hyperparameters tuned on the validation set. The models were trained to minimize the mean squared error (MSE). Models with the best performance on the validation set were evaluated on the testing set according to 1) MSE, 2) buffer accuracy, and 3) classification accuracy, with results compared to a mean regressor. RESULTS A total of 302,300 patients were included in this study. During validation, the PyTorch MLPs had the best MSEs for DOS (0.918) and LOS (0.715). During testing, the PyTorch MLPs similarly performed best based on MSEs for DOS (0.896) and LOS (0.690). While the scikit-learn MLP yielded the best 30-minute buffer accuracy for DOS (78.8%), the PyTorch MLP provided the best 1-day buffer accuracy for LOS (75.2%). Nearly all the ML models were more accurate than the mean regressors for both DOS and LOS. CONCLUSION Conventional and deep learning models performed better than mean regressors for predicting DOS and LOS of unilateral elective TKA patients based on preoperative factors. Future work should include operational factors to improve overall predictions.
Collapse
Affiliation(s)
- Aazad Abbas
- Temerty Faculty of Medicine, University of Toronto, 1 King's College Circle, Toronto, ON M5S 1A8, Canada; Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada.
| | - Jacob Mosseri
- Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada; Department of Mechanical and Industrial Engineering, University of Toronto, 5 King's College Road, Toronto, ON M5S 3G8, Canada.
| | - Johnathan R Lex
- Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada; Division of Orthopaedic Surgery, University of Toronto, 149 College Street Room 508-A, Toronto, ON M5T 1P5, Canada
| | - Jay Toor
- Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada; Division of Orthopaedic Surgery, University of Toronto, 149 College Street Room 508-A, Toronto, ON M5T 1P5, Canada.
| | - Bheeshma Ravi
- Division of Orthopaedic Surgery, University of Toronto, 149 College Street Room 508-A, Toronto, ON M5T 1P5, Canada; Division of Orthopaedic Surgery, Sunnybrook Health Science Centre, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada.
| | - Elias B Khalil
- Department of Mechanical and Industrial Engineering, University of Toronto, 5 King's College Road, Toronto, ON M5S 3G8, Canada.
| | - Cari Whyne
- Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada; Division of Orthopaedic Surgery, University of Toronto, 149 College Street Room 508-A, Toronto, ON M5T 1P5, Canada; Division of Orthopaedic Surgery, Sunnybrook Health Science Centre, 2075 Bayview Avenue, Toronto, ON M4N 3M5, Canada.
| |
Collapse
|
34
|
Bishop JA, Javed HA, el-Bouri R, Zhu T, Taylor T, Peto T, Watkinson P, Eyre DW, Clifton DA. Improving patient flow during infectious disease outbreaks using machine learning for real-time prediction of patient readiness for discharge. PLoS One 2021; 16:e0260476. [PMID: 34813632 PMCID: PMC8610279 DOI: 10.1371/journal.pone.0260476] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2021] [Accepted: 11/10/2021] [Indexed: 11/19/2022] Open
Abstract
BACKGROUND Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis. METHODS AND PERFORMANCE Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients' real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models' inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within the following 24 hours. The 20% of patients with the highest ranking are considered as candidates for discharge and would therefore expect to have a further screening by a clinician to confirm whether they are ready for discharge or not. Performance was evaluated in terms of positive predictive value (PPV), i.e., the proportion of these patients who would have been correctly deemed as 'ready for discharge' after having the second screening by a clinician. Performance was high for patients on their first day of admission (PPV = 0.96/0.94 for planned/emergency patients respectively) but dropped for patients further into a longer admission (PPV = 0.66/0.71 for planned/emergency patients still in hospital after 7 days). CONCLUSION We demonstrate the efficacy of machine learning methods at making operationally focused, next-day discharge readiness predictions for all individual patients in hospital at any given moment and propose a strategy for their use within a decision-support tool during crisis periods.
Collapse
Affiliation(s)
- Jennifer A. Bishop
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Hamza A. Javed
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Rasheed el-Bouri
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Tingting Zhu
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Thomas Taylor
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Tim Peto
- Oxford University Hospitals NHS Foundation Trust, Oxford, United Kingdom
| | - Peter Watkinson
- Oxford University Hospitals NHS Foundation Trust, Oxford, United Kingdom
| | - David W. Eyre
- Oxford University Hospitals NHS Foundation Trust, Oxford, United Kingdom
- Big Data Institute, Nuffield Department of Population Health, University of Oxford, Oxford, United Kingdom
| | - David A. Clifton
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
35
|
Naemi A, Schmidt T, Mansourvar M, Ebrahimi A, Wiil UK. Quantifying the impact of addressing data challenges in prediction of length of stay. BMC Med Inform Decis Mak 2021; 21:298. [PMID: 34749708 PMCID: PMC8576901 DOI: 10.1186/s12911-021-01660-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2021] [Accepted: 10/17/2021] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower. METHODS In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender. RESULTS The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values. CONCLUSION We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.
Collapse
Affiliation(s)
- Amin Naemi
- Center for Health Informatics and Technology, The Maersk Mc-Kinney Institute, University of Southern Denmark, Odense, Denmark.
| | - Thomas Schmidt
- Center for Health Informatics and Technology, The Maersk Mc-Kinney Institute, University of Southern Denmark, Odense, Denmark
| | - Marjan Mansourvar
- Department of Mathematics and Computer Science (IMADA), University of Southern Denmark, Odense, Denmark
| | - Ali Ebrahimi
- Center for Health Informatics and Technology, The Maersk Mc-Kinney Institute, University of Southern Denmark, Odense, Denmark
| | - Uffe Kock Wiil
- Center for Health Informatics and Technology, The Maersk Mc-Kinney Institute, University of Southern Denmark, Odense, Denmark
| |
Collapse
|
36
|
Lin WT, Wu TY, Chen YJ, Chang YS, Lin CH, Lin YJ. Predicting in-hospital length of stay for very-low-birth-weight preterm infants using machine learning techniques. J Formos Med Assoc 2021; 121:1141-1148. [PMID: 34629242 DOI: 10.1016/j.jfma.2021.09.018] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2021] [Revised: 09/01/2021] [Accepted: 09/24/2021] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND/PURPOSE The in-hospital length of stay (LOS) among very-low-birth-weight (VLBW, BW < 1500 g) infants is an index for care quality and affects medical resource allocation. We aimed to analyze the LOS among VLBW infants in Taiwan, and to develop and compare the performance of different LOS prediction models using machine learning (ML) techniques. METHODS This retrospective study illustrated LOS data from VLBW infants born between 2016 and 2018 registered in the Taiwan Neonatal Network. Among infants discharged alive, continuous variables (LOS or postmenstrual age, PMA) and categorical variables (late and non-late discharge group) were used as outcome variables to build prediction models. We used 21 early neonatal variables and six algorithms. The performance was compared using the coefficient of determination (R2) for continuous variables and area under the curve (AUC) for categorical variables. RESULTS A total of 3519 VLBW infants were included to illustrate the profile of LOS. We found 59% of mortalities occurred within the first 7 days after birth. The median of LOS among surviving and deceased infants was 62 days and 5 days. For the ML prediction models, 2940 infants were enrolled. Prediction of LOS or PMA had R2 values less than 0.6. Among the prediction models for prolonged LOS, the logistic regression (ROC: 0.724) and random forest (ROC: 0.712) approach had better performance. CONCLUSION We provide a benchmark of LOS among VLBW infants in each gestational age group in Taiwan. ML technique can improve the accuracy of the prediction model of prolonged LOS of VLBW.
Collapse
Affiliation(s)
- Wei-Ting Lin
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan
| | - Tsung-Yu Wu
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan
| | - Yen-Ju Chen
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan
| | - Yu-Shan Chang
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan
| | - Chyi-Her Lin
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan; Department of Pediatrics, E-Da Hospital, College of Medicine, I-Shou University, Kaohsiung, Taiwan
| | - Yuh-Jyh Lin
- Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng-Kung University, Tainan, Taiwan.
| |
Collapse
|
37
|
Lequertier V, Wang T, Fondrevelle J, Augusto V, Duclos A. Hospital Length of Stay Prediction Methods: A Systematic Review. Med Care 2021; 59:929-938. [PMID: 34310455 DOI: 10.1097/mlr.0000000000001596] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
OBJECTIVE This systematic review sought to establish a picture of length of stay (LOS) prediction methods based on available hospital data and study protocols designed to measure their performance. MATERIALS AND METHODS An English literature search was done relative to hospital LOS prediction from 1972 to September 2019 according to the PRISMA guidelines. Articles were retrieved from PubMed, ScienceDirect, and arXiv databases. Information were extracted from the included papers according to a standardized assessment of population setting and study sample, data sources and input variables, LOS prediction methods, validation study design, and performance evaluation metrics. RESULTS Among 74 selected articles, 98.6% (73/74) used patients' data to predict LOS; 27.0% (20/74) used temporal data; and 21.6% (16/74) used the data about hospitals. Overall, regressions were the most popular prediction methods (64.9%, 48/74), followed by machine learning (20.3%, 15/74) and deep learning (17.6%, 13/74). Regarding validation design, 35.1% (26/74) did not use a test set, whereas 47.3% (35/74) used a separate test set, and 17.6% (13/74) used cross-validation. The most used performance metrics were R2 (47.3%, 35/74), mean squared (or absolute) error (24.4%, 18/74), and the accuracy (14.9%, 11/74). Over the last decade, machine learning and deep learning methods became more popular (P=0.016), and test sets and cross-validation got more and more used (P=0.014). CONCLUSIONS Methods to predict LOS are more and more elaborate and the assessment of their validity is increasingly rigorous. Reducing heterogeneity in how these methods are used and reported is key to transparency on their performance.
Collapse
Affiliation(s)
- Vincent Lequertier
- Research on Healthcare Performance (RESHAPE), Université Claude Bernard Lyon 1, INSERM U1290
- Health Data Department, Lyon University Hospital, Lyon
- Univ Lyon, INSA Lyon, Université Claude Bernard Lyon 1, Univ Lumière Lyon 2, DISP, EA4570, 69621 Villeurbanne, France
| | - Tao Wang
- University of Lyon, INSA Lyon, Université Claude Bernard Lyon 1, Univ Lumière Lyon 2, UJM-Saint-Etienne, Decision and Information Systems for Production systems (DISP), Villeurbanne Cedex
| | - Julien Fondrevelle
- Univ Lyon, INSA Lyon, Université Claude Bernard Lyon 1, Univ Lumière Lyon 2, DISP, EA4570, 69621 Villeurbanne, France
| | - Vincent Augusto
- Mines Saint-Etienne, University of Clermont Auvergne, CNRS, UMR 6158 LIMOS, Centre CIS, Saint-Etienne, France
| | - Antoine Duclos
- Research on Healthcare Performance (RESHAPE), Université Claude Bernard Lyon 1, INSERM U1290
- Health Data Department, Lyon University Hospital, Lyon
| |
Collapse
|
38
|
Petch J, Di S, Nelson W. Opening the black box: the promise and limitations of explainable machine learning in cardiology. Can J Cardiol 2021; 38:204-213. [PMID: 34534619 DOI: 10.1016/j.cjca.2021.09.004] [Citation(s) in RCA: 122] [Impact Index Per Article: 40.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 08/23/2021] [Accepted: 09/08/2021] [Indexed: 11/29/2022] Open
Abstract
Many clinicians remain wary of machine learning due to long-standing concerns about "black box" models. "Black box" is shorthand for models that are sufficiently complex that they are not straightforwardly interpretable to humans. Lack of interpretability in predictive models can undermine trust in those models, especially in health care where so many decisions are literally life and death. There has recently been an explosion of research in the field of explainable machine learning aimed at addressing these concerns. The promise of explainable machine learning is considerable, but it is important for cardiologists who may encounter these techniques in clinical decision support tools or novel research papers to have a critical understanding of both their strengths and their limitations. This paper reviews key concepts and techniques in the field of explainable machine learning as they apply to cardiology. Key concepts reviewed include interpretability versus explainability and global versus local explanations. Techniques demonstrated include permutation importance, surrogate decision trees, local interpretable model-agnostic explanations, and partial dependence plots. We discuss several limitations with explainability techniques, focusing on the how the nature of explanations as approximations may omit important information about how black box models work and why they make certain predictions. We conclude by proposing a rule of thumb about when it is appropriate to use black box models with explanations, rather than interpretable models.
Collapse
Affiliation(s)
- Jeremy Petch
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Institute of Health Policy, Management and Evaluation, University of Toronto; Division of Cardiology, Department of Medicine, McMaster University; Population Health Research Institute.
| | - Shuang Di
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Dalla Lana School of Public Health, University of Toronto
| | - Walter Nelson
- Centre for Data Science and Digital Health, Hamilton Health Sciences; Department of Statistical Sciences, University of Toronto
| |
Collapse
|
39
|
Vîjan AE, Daha IC, Delcea C, Dan GA. Determinants of Prolonged Length of Hospital Stay of Patients with Atrial Fibrillation. J Clin Med 2021; 10:jcm10163715. [PMID: 34442009 PMCID: PMC8396858 DOI: 10.3390/jcm10163715] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Revised: 08/02/2021] [Accepted: 08/17/2021] [Indexed: 11/24/2022] Open
Abstract
Background and Aim: The increasing prevalence and high hospitalization rates make atrial fibrillation (AF) a significant healthcare strain. However, there are limited data regarding the length of hospital stay (LOS) of AF patients. Our purpose was to determine the main drivers of extended LOS of AF patients. Methods: All AF patients, hospitalized consecutively in a tertiary cardiology center, from January 2018 to February 2020 were included in this retrospective cohort study. Readmissions were excluded. Prolonged LOS was defined as more than seven days (the upper limit of the third quartile). Results: Our study included 949 AF patients, 52.9% females. The mean age was 72.5 ± 10.3 years. The median LOS was 4 days. A total of 28.7% had an extended LOS. Further, 82.9% patients had heart failure (HF). In multivariable analysis, the independent predictors of extended LOS were: acute coronary syndromes (ACS) (HR 4.60, 95% CI 1.66–12.69), infections (HR 2.61, 95% CI 1.44–3.23), NT-proBNP > 1986 ng/mL (HR 1.96, 95% CI 1.37–2.82), acute decompensated HF (ADHF) (HR 1.76, 95% CI 1.23–2.51), HF with reduced ejection fraction (HFrEF) (HR 1.69, 95% CI 1.15–2.47) and the HAS-BLED score (HR 1.42, 95% CI 1.14–1.78). Conclusion: ACS, ADHF, HFrEF, increased NT-proBNP levels, infections and elevated HAS-BLED were independent predictors of extended LOS, while specific clinical or therapeutical AF characteristics were not.
Collapse
Affiliation(s)
- Ancuța Elena Vîjan
- Internal Medicine and Cardiology Department, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania; (A.E.V.); (I.C.D.); (G.-A.D.)
- Cardiology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania
| | - Ioana Cristina Daha
- Internal Medicine and Cardiology Department, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania; (A.E.V.); (I.C.D.); (G.-A.D.)
- Cardiology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania
| | - Caterina Delcea
- Internal Medicine and Cardiology Department, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania; (A.E.V.); (I.C.D.); (G.-A.D.)
- Cardiology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania
- Correspondence:
| | - Gheorghe-Andrei Dan
- Internal Medicine and Cardiology Department, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania; (A.E.V.); (I.C.D.); (G.-A.D.)
- Cardiology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania
| |
Collapse
|
40
|
Pappada SM. Machine learning in medicine: It has arrived, let's embrace it. J Card Surg 2021; 36:4121-4124. [PMID: 34392567 DOI: 10.1111/jocs.15918] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2021] [Accepted: 08/08/2021] [Indexed: 11/28/2022]
Abstract
Machine learning and artificial intelligence (AI) have arrived in medicine and the healthcare community is experiencing significant growth in their adoption across numerous patient care settings. There are countless applications for machine learning and AI in medicine ranging from patient outcome prediction, to clinical decision support, to predicting future patient therapeutic setpoints. This commentary discusses a recent application leveraging machine learning to predict one-year patient survival following orthotopic heart transplantation. This modeling approach has significant implications in terms of improving clinical decision-making, patient counseling, and ultimately organ allocation and has been shown to significantly outperform pre-existing algorithms. This commentary also discusses how adoption and advancement of this modeling approach in the future can provide increased personalization of patient care. The continued expansion of information systems and growth of electronic patient data sources in health care will continue to pave the way for increased use and adoption of data science in medicine. Personalized medicine has been a long-standing goal of the healthcare community and with machine learning and AI now being continually incorporated into clinical settings and practice, this technology is well on the pathway to make a considerable impact to greatly improve patient care in the near future.
Collapse
Affiliation(s)
- Scott M Pappada
- Department of Anesthesiology, College of Medicine, The University of Toledo, Toledo, Ohio, USA.,Department of Bioengineering, The University of Toledo, Toledo, Ohio, USA.,Department of Electrical Engineering and Computer Science, The University of Toledo, Toledo, Ohio, USA.,Department of Anesthesiology, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| |
Collapse
|
41
|
Prolonged hospital length of stay in pediatric trauma: a model for targeted interventions. Pediatr Res 2021; 90:464-471. [PMID: 33184499 DOI: 10.1038/s41390-020-01237-0] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/23/2020] [Revised: 09/17/2020] [Accepted: 10/11/2020] [Indexed: 11/08/2022]
Abstract
BACKGROUND In this study, trauma-specific risk factors of prolonged length of stay (LOS) in pediatric trauma were examined. Statistical and machine learning models were used to proffer ways to improve the quality of care of patients at risk of prolonged length of stay and reduce cost. METHODS Data from 27 hospitals were retrieved on 81,929 hospitalizations of pediatric patients with a primary diagnosis of trauma, and for which the LOS was >24 h. Nested mixed effects model was used for simplified statistical inference, while a stochastic gradient boosting model, considering high-order statistical interactions, was built for prediction. RESULTS Over 18.7% of the encounters had LOS >1 week. Burns and corrosion and suspected and confirmed child abuse are the strongest drivers of prolonged LOS. Several other trauma-specific and general pediatric clinical variables were also predictors of prolonged LOS. The stochastic gradient model obtained an area under the receiver operator characteristic curve of 0.912 (0.907, 0.917). CONCLUSIONS The high performance of the machine learning model coupled with statistical inference from the mixed effects model provide an opportunity for targeted interventions to improve quality of care of trauma patients likely to require long length of stay. IMPACT Targeted interventions on high-risk patients would improve the quality of care of pediatric trauma patients and reduce the length of stay. This comprehensive study includes data from multiple hospitals analyzed with advanced statistical and machine learning models. The statistical and machine learning models provide opportunities for targeted interventions and reduction in prolonged length of stay reducing the burden of hospitalization on families.
Collapse
|
42
|
Yu K, Yang Z, Wu C, Huang Y, Xie X. In-hospital resource utilization prediction from electronic medical records with deep learning. Knowl Based Syst 2021. [DOI: 10.1016/j.knosys.2021.107052] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
43
|
Bibicheva TS, Skazkina VV, Ogneva MV, Simonyan MA, Gridnev VI, Karavaev AS. Missing value imputation with linear methods in the database of cardiological patients in prediction of mortality. CARDIO-IT 2021. [DOI: 10.15275/cardioit.2021.0101] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022] Open
Abstract
This study examines missing value imputation in the Russian Acute Coronary Syndrome Registry (RusACSR) and assessment of the probability of predicting mortality. Linear methods with the most probable or average value were used for imputation. The prediction problem was solved using the k-nearest neighbors method. This work reveals that the imputation method, despite their simplicity, increases the probability of prediction of mortality by 6%.
Collapse
|
44
|
Prediction of arrhythmia after intervention in children with atrial septal defect based on random forest. BMC Pediatr 2021; 21:280. [PMID: 34134641 PMCID: PMC8207618 DOI: 10.1186/s12887-021-02744-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Accepted: 05/27/2021] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Using random forest to predict arrhythmia after intervention in children with atrial septal defect. METHODS We constructed a prediction model of complications after interventional closure for children with atrial septal defect. The model was based on random forest, and it solved the need for postoperative arrhythmia risk prediction and assisted clinicians and patients' families to make preoperative decisions. RESULTS Available risk prediction models provided patients with specific risk factor assessments, we used Synthetic Minority Oversampling Technique algorithm and random forest machine learning to propose a prediction model, and got a prediction accuracy of 94.65 % and an Area Under Curve value of 0.8956. CONCLUSIONS Our study was based on the model constructed by random forest, which can effectively predict the complications of arrhythmia after interventional closure in children with atrial septal defect.
Collapse
|
45
|
Predicting need for hospital-specific interventional care after surgery using electronic health record data. Surgery 2021; 170:790-796. [PMID: 34090676 DOI: 10.1016/j.surg.2021.05.005] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2020] [Revised: 04/23/2021] [Accepted: 05/04/2021] [Indexed: 12/25/2022]
Abstract
BACKGROUND A significant proportion of surgical inpatients is often admitted longer than necessary. Early identification of patients who do not need care that is strictly provided within hospitals would allow timely discharge of patients to a postoperative nursing home for further recovery. We aimed to develop a model to predict whether a patient needs hospital-specific interventional care beyond the second postoperative day. METHODS This study included all adult patients discharged from surgical care in the surgical oncology department from June 2017 to February 2020. The primary outcome was to predict whether a patient still needs hospital-specific interventional care beyond the second postoperative day. Hospital-specific care was defined as unplanned reoperations, radiological interventions, and intravenous antibiotics administration. Different analytical methods were compared with respect to the area under the receiver-operating characteristics curve, sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS Each model was trained on 1,174 episodes. In total, 847 (50.5%) patients required an intervention during postoperative admission. A random forest model performed best with an area under the receiver-operating characteristics curve of 0.88 (95% confidence interval 0.83-0.93), sensitivity of 79.1% (95% confidence interval 0.67-0.92), specificity of 80.0% (0.73-0.87), positive predictive value of 57.6% (0.45-0.70) and negative predictive value of 91.7% (0.87-0.97). CONCLUSION This proof-of-concept study found that a random forest model could successfully predict whether a patient could be safely discharged to a nursing home and does not need hospital care anymore. Such a model could aid hospitals in addressing capacity challenges and improve patient flow, allowing for timely surgical care.
Collapse
|
46
|
El-Bouri R, Taylor T, Youssef A, Zhu T, Clifton DA. Machine learning in patient flow: a review. PROGRESS IN BIOMEDICAL ENGINEERING (BRISTOL, ENGLAND) 2021; 3:022002. [PMID: 34738074 PMCID: PMC8559147 DOI: 10.1088/2516-1091/abddc5] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/30/2020] [Revised: 01/18/2021] [Accepted: 01/20/2021] [Indexed: 12/13/2022]
Abstract
This work is a review of the ways in which machine learning has been used in order to plan, improve or aid the problem of moving patients through healthcare services. We decompose the patient flow problem into four subcategories: prediction of demand on a healthcare institution, prediction of the demand and resource required to transfer patients from the emergency department to the hospital, prediction of potential resource required for the treatment and movement of inpatients and prediction of length-of-stay and discharge timing. We argue that there are benefits to both approaches of considering the healthcare institution as a whole as well as the patient by patient case and that ideally a combination of these would be best for improving patient flow through hospitals. We also argue that it is essential for there to be a shared dataset that will allow researchers to benchmark their algorithms on and thereby allow future researchers to build on that which has already been done. We conclude that machine learning for the improvement of patient flow is still a young field with very few papers tailor-making machine learning methods for the problem being considered. Future works should consider the need to transfer algorithms trained on a dataset to multiple hospitals and allowing for dynamic algorithms which will allow real-time decision-making to help clinical staff on the shop floor.
Collapse
Affiliation(s)
- Rasheed El-Bouri
- Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom
| | - Thomas Taylor
- Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom
| | - Alexey Youssef
- Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom
| | - Tingting Zhu
- Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom
| | - David A Clifton
- Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
47
|
Binkheder S, Aldekhyyel R, Almulhem J. Health informatics publication trends in Saudi Arabia: a bibliometric analysis over the last twenty-four years. J Med Libr Assoc 2021; 109:219-239. [PMID: 34285665 PMCID: PMC8270356 DOI: 10.5195/jmla.2021.1072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
OBJECTIVE Understanding health informatics (HI) publication trends in Saudi Arabia may serve as a framework for future research efforts and contribute toward meeting national "e-Health" goals. The authors' intention was to understand the state of the HI field in Saudi Arabia by exploring publication trends and their alignment with national goals. METHODS A scoping review was performed to identify HI publications from Saudi Arabia in PubMed, Embase, and Web of Science. We analyzed publication trends based on topics, keywords, and how they align with the Ministry of Health's (MOH's) "digital health journey" framework. RESULTS The total number of publications included was 242. We found 1 (0.4%) publication in 1995-1999, 11 (4.5%) publications in 2000-2009, and 230 (95.0%) publications in 2010-2019. We categorized publications into 3 main HI fields and 4 subfields: 73.1% (n=177) of publications were in clinical informatics (85.1%, n=151 medical informatics; 5.6%, n=10 pharmacy informatics; 6.8%, n=12 nursing informatics; 2.3%, n=4 dental informatics); 22.3% (n=54) were in consumer health informatics; and 4.5% (n=11) were in public health informatics. The most common keyword was "medical informatics" (21.5%, n=52). MOH framework-based analysis showed that most publications were categorized as "digitally enabled care" and "digital health foundations." CONCLUSIONS The years of 2000-2009 may be seen as an infancy stage of the HI field in Saudi Arabia. Exploring how the Saudi Arabian MOH's e-Health initiatives may influence research is valuable for advancing the field. Data exchange and interoperability, artificial intelligence, and intelligent health enterprises might be future research directions in Saudi Arabia.
Collapse
Affiliation(s)
- Samar Binkheder
- , Assistant Professor of Biomedical and Health Informatics, College of Medicine, King Saud University, Riyadh, Kingdom of Saudi Arabia
| | - Raniah Aldekhyyel
- , Assistant Professor of Biomedical and Health Informatics, College of Medicine, King Saud University, Riyadh, Kingdom of Saudi Arabia
| | - Jwaher Almulhem
- , Assistant Professor of Biomedical and Health Informatics, College of Medicine, King Saud University, Riyadh, Kingdom of Saudi Arabia
| |
Collapse
|
48
|
Triana AJ, Vyas R, Shah AS, Tiwari V. Predicting Length of Stay of Coronary Artery Bypass Grafting Patients Using Machine Learning. J Surg Res 2021; 264:68-75. [PMID: 33784585 DOI: 10.1016/j.jss.2021.02.003] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Revised: 01/19/2021] [Accepted: 02/17/2021] [Indexed: 12/19/2022]
Abstract
BACKGROUND There is a growing need to identify which bits of information are most valuable for healthcare providers. The aim of this study was to search for the highest impact variables in predicting postsurgery length of stay (LOS) for patients who undergo coronary artery bypass grafting (CABG). MATERIALS AND METHODS Using a single institution's Society of Thoracic Surgeons (STS) Registry data, 2121 patients with elective or urgent, isolated CABG were analyzed across 116 variables. Two machine learning techniques of random forest and artificial neural networks (ANNs) were used to search for the highest impact variables in predicting LOS, and results were compared against multiple linear regression. Out-of-sample validation of the models was performed on 105 patients. RESULTS Of the 10 highest impact variables identified in predicting LOS, four of the most impactful variables were duration intubated, last preoperative creatinine, age, and number of intraoperative packed red blood cell transfusions. The best performing model was an ANN using the ten highest impact variables (testing sample mean absolute error (MAE) = 1.685 d, R2 = 0.232), which performed consistently in the out-of-sample validation (MAE = 1.612 d, R2 = 0.150). CONCLUSION Using machine learning, this study identified several novel predictors of postsurgery LOS and reinforced certain known risk factors. Out of the entire STS database, only a few variables carry most of the predictive value for LOS in this population. With this knowledge, a simpler linear regression model has been shared and could be used elsewhere after further validation.
Collapse
Affiliation(s)
- Austin J Triana
- Vanderbilt University School of Medicine, Nashville, Tennessee.
| | - Rushikesh Vyas
- Vanderbilt University Medical Center, Department of Cardiac Surgery, Nashville, Tennessee; Vanderbilt University Medical Center, Department of Thoracic Surgery, Nashville, Tennessee
| | - Ashish S Shah
- Vanderbilt University Medical Center, Department of Cardiac Surgery, Nashville, Tennessee
| | - Vikram Tiwari
- Vanderbilt University Medical Center, Department of Anesthesiology, Nashville, Tennessee; Vanderbilt University Medical Center, Department of Biomedical Informatics, Nashville, Tennessee; Vanderbilt University Medical Center, Department of Biostatistics, Nashville, Tennessee; Vanderbilt University Medical Center Surgical Analytics, Nashville, Tennessee; Vanderbilt University Owen Graduate School of Management, Nashville, Tennessee
| |
Collapse
|
49
|
Tong J, Liu P, Ji M, Wang Y, Xue Q, Yang JJ, Zhou CM. Machine Learning Can Predict Total Death After Radiofrequency Ablation in Liver Cancer Patients. CLINICAL MEDICINE INSIGHTS-ONCOLOGY 2021; 15:11795549211000017. [PMID: 33854400 PMCID: PMC8013536 DOI: 10.1177/11795549211000017] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/14/2020] [Accepted: 02/07/2021] [Indexed: 01/10/2023]
Abstract
Objective: Over 1 million new cases of hepatocellular carcinoma (HCC) are diagnosed worldwide every year. Its prognosis remains poor, and the 5-year survival rate in all disease stages is estimated to be between 10% and 20%. Radiofrequency ablation (RFA) has become an important local treatment for liver cancer, and machine learning (ML) can provide many shortcuts for liver cancer medical research. Therefore, we explore the role of ML in predicting the total mortality of liver cancer patients undergoing RFA. Methods: This study is a secondary analysis of public database data from 578 liver cancer patients. We used Python for ML to establish the prognosis model. Results: The results showed that the 5 most important factors were platelet count (PLT), Alpha-fetoprotein (AFP), age, tumor size, and total bilirubin, respectively. Results of the total death model for liver cancer patients in test group: among the 5 algorithm models, the highest accuracy rate was that of gbm (0.681), followed by the Logistic algorithm (0.672); among the 5 algorithms, area under the curve (AUC) values, from high to low, were Logistic (0.738), DecisionTree (0.723), gbm (0.717), GradientBoosting (0.714), and Forest (0.693); Among the 5 algorithms, gbm had the highest precision rate (0.721), followed by the Logistic algorithm (0.714). Among the 5 algorithms, DecisionTree had the highest recall rate (0.642), followed by the GradientBoosting algorithm (0.571). Conclusion: Machine learning can predict total death after RFA in liver cancer patients. Therefore, ML research has great potential for both personalized treatment and prognosis of liver cancer.
Collapse
Affiliation(s)
- Jianhua Tong
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Panmiao Liu
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Muhuo Ji
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Ying Wang
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Qiong Xue
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Jian-Jun Yang
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Cheng-Mao Zhou
- Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| |
Collapse
|
50
|
Key Experimental Factors of Machine Learning-Based Identification of Surgery Cancellations. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:6247652. [PMID: 33688420 PMCID: PMC7914093 DOI: 10.1155/2021/6247652] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/06/2019] [Revised: 01/21/2020] [Accepted: 02/13/2021] [Indexed: 02/05/2023]
Abstract
This study aimed to provide effective methods for the identification of surgeries with high cancellation risk based on machine learning models and analyze the key factors that affect the identification performance. The data covered the period from January 1, 2013, to December 31, 2014, at West China Hospital in China, which focus on elective urologic surgeries. All surgeries were scheduled one day in advance, and all cancellations were of institutional resource- and capacity-related types. Feature selection strategies, machine learning models, and sampling methods are the most discussed topic in general machine learning researches and have a direct impact on the performance of machine learning models. Hence, they were considered to systematically generate complete schemes in machine learning-based identification of surgery cancellations. The results proved the feasibility and robustness of identifying surgeries with high cancellation risk, with the considerable maximum of area under the curve (AUC) (0.7199) for random forest model with original sampling using backward selection strategy. In addition, one-side Delong test and sum of square error analysis were conducted to measure the effects of feature selection strategy, machine learning model, and sampling method on the identification of surgeries with high cancellation risk, and the selection of machine learning model was identified as the key factors that affect the identification of surgeries with high cancellation risk. This study offers methodology and insights for identifying the key experimental factors for identifying surgery cancellations, and it is helpful to further research on machine learning-based identification of surgeries with high cancellation risk.
Collapse
|