1
|
Ser SE, Shear K, Snigurska UA, Prosperi M, Wu Y, Magoc T, Bjarnadottir RI, Lucero RJ. Clinical Prediction Models for Hospital-Induced Delirium Using Structured and Unstructured Electronic Health Record Data: Protocol for a Development and Validation Study. JMIR Res Protoc 2023; 12:e48521. [PMID: 37943599 PMCID: PMC10667972 DOI: 10.2196/48521] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Revised: 09/01/2023] [Accepted: 09/05/2023] [Indexed: 11/10/2023] Open
Abstract
BACKGROUND Hospital-induced delirium is one of the most common and costly iatrogenic conditions, and its incidence is predicted to increase as the population of the United States ages. An academic and clinical interdisciplinary systems approach is needed to reduce the frequency and impact of hospital-induced delirium. OBJECTIVE The long-term goal of our research is to enhance the safety of hospitalized older adults by reducing iatrogenic conditions through an effective learning health system. In this study, we will develop models for predicting hospital-induced delirium. In order to accomplish this objective, we will create a computable phenotype for our outcome (hospital-induced delirium), design an expert-based traditional logistic regression model, leverage machine learning techniques to generate a model using structured data, and use machine learning and natural language processing to produce an integrated model with components from both structured data and text data. METHODS This study will explore text-based data, such as nursing notes, to improve the predictive capability of prognostic models for hospital-induced delirium. By using supervised and unsupervised text mining in addition to structured data, we will examine multiple types of information in electronic health record data to predict medical-surgical patient risk of developing delirium. Development and validation will be compliant to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement. RESULTS Work on this project will take place through March 2024. For this study, we will use data from approximately 332,230 encounters that occurred between January 2012 to May 2021. Findings from this project will be disseminated at scientific conferences and in peer-reviewed journals. CONCLUSIONS Success in this study will yield a durable, high-performing research-data infrastructure that will process, extract, and analyze clinical text data in near real time. This model has the potential to be integrated into the electronic health record and provide point-of-care decision support to prevent harm and improve quality of care. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/48521.
Collapse
Affiliation(s)
- Sarah E Ser
- Department of Epidemiology, College of Public Health and Health Professions and College of Medicine, University of Florida, Gainesville, FL, United States
| | - Kristen Shear
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, Gainesville, FL, United States
| | - Urszula A Snigurska
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, Gainesville, FL, United States
| | - Mattia Prosperi
- Department of Epidemiology, College of Public Health and Health Professions and College of Medicine, University of Florida, Gainesville, FL, United States
| | - Yonghui Wu
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL, United States
| | - Tanja Magoc
- Integrated Data Repository Research Services, University of Florida, Gainesville, FL, United States
| | - Ragnhildur I Bjarnadottir
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, Gainesville, FL, United States
| | - Robert J Lucero
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, Gainesville, FL, United States
- School of Nursing, University of California Los Angeles, Los Angeles, CA, United States
| |
Collapse
|
2
|
Anik FI, Sakib N, Shahriar H, Xie Y, Nahiyan HA, Ahamed SI. Unraveling a blockchain-based framework towards patient empowerment: A scoping review envisioning future smart health technologies. Smart Health (Amst) 2023; 29:100401. [PMID: 37200573 PMCID: PMC10102703 DOI: 10.1016/j.smhl.2023.100401] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Revised: 01/15/2023] [Accepted: 04/10/2023] [Indexed: 05/20/2023]
Abstract
The COVID-19 pandemic shows us how crucial patient empowerment can be in the healthcare ecosystem. Now, we know that scientific advancement, technology integration, and patient empowerment need to be orchestrated to realize future smart health technologies. In that effort, this paper unravels the Good (advantages), Bad (challenges/limitations), and Ugly (lacking patient empowerment) of the blockchain technology integration in the Electronic Health Record (EHR) paradigm in the existing healthcare landscape. Our study addresses four methodically-tailored and patient-centric Research Questions, primarily examining 138 relevant scientific papers. This scoping review also explores how the pervasiveness of blockchain technology can help to empower patients in terms of access, awareness, and control. Finally, this scoping review leverages the insights gleaned from this study and contributes to the body of knowledge by proposing a patient-centric blockchain-based framework. This work will envision orchestrating three essential elements with harmony: scientific advancement (Healthcare and EHR), technology integration (Blockchain Technology), and patient empowerment (access, awareness, and control).
Collapse
Affiliation(s)
- Fahim Islam Anik
- Department of Mechanical Engineering, Khulna University of Engineering & Technology, Khulna, Bangladesh
| | - Nazmus Sakib
- Department of Information Technology, Kennesaw State University, GA, USA
| | - Hossain Shahriar
- Department of Information Technology, Kennesaw State University, GA, USA
| | - Yixin Xie
- Department of Information Technology, Kennesaw State University, GA, USA
| | - Helal An Nahiyan
- Department of Mechanical Engineering, Khulna University of Engineering & Technology, Khulna, Bangladesh
| | | |
Collapse
|
3
|
Silva APD, Santos HDPD, Rotta ALO, Baiocco GG, Vieira R, Urbanetto JDS. Risco de queda relacionado a medicamentos em hospitais: abordagem de aprendizado de máquina. ACTA PAUL ENFERM 2023; 36. [DOI: 10.37689/acta-ape/2023ao00771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023] Open
|
4
|
Hsu Y, Kao YS. Can the Electronic Health Record Predict Risk of Falls in Hospitalized Patients by Using Artificial Intelligence? A Meta-analysis. Comput Inform Nurs 2022. [PMID: 36731013 DOI: 10.1097/CIN.0000000000000952] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
Because of an aging population worldwide, the increasing prevalence of falls and their consequent injuries are becoming a safety, health, and social-care issue among elderly people. We conducted a meta-analysis to investigate the benchmark of prediction power when using the EHR with artificial intelligence to predict risk of falls in hospitalized patients. The CHARMS guideline was used in this meta-analysis. We searched PubMed, Cochrane, and EMBASE. The pooled sensitivity and specificity were calculated, and the summary receiver operating curve was formed to investigate the predictive power of artificial intelligence models. The PROBAST table was used to assess the quality of the selected studies. A total of 132 846 patients were included in this meta-analysis. The pooled area under the curve of the collected research was estimated to be 0.78. The pooled sensitivity was 0.63 (95% confidence interval, 0.52-0.72), whereas the pooled specificity was 0.82 (95% confidence interval, 0.73-0.88). The quality of our selected studies was high, with most of them being evaluated with low risk of bias and low concern for applicability. Our study demonstrates that using the EHR with artificial intelligence to predict the risk of falls among hospitalized patients is feasible. Future clinical applications are anticipated.
Collapse
|
5
|
Bernet NS, Everink IHJ, Schols JMGA, Halfens RJG, Richter D, Hahn S. Hospital performance comparison of inpatient fall rates; the impact of risk adjusting for patient-related factors: a multicentre cross-sectional survey. BMC Health Serv Res 2022; 22:225. [PMID: 35180859 PMCID: PMC8857794 DOI: 10.1186/s12913-022-07638-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2021] [Accepted: 02/14/2022] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND Comparing inpatient fall rates can serve as a benchmark for quality improvement. To improve the comparability of performance between hospitals, adjustments for patient-related fall risk factors that are not modifiable by care are recommended. Thereafter, the remaining variability in risk-adjusted fall rates can be attributed to differences in quality of care provided by a hospital. Research on risk-adjusted fall rates and their impact on hospital comparisons is currently sparse. Therefore, the aims of this study were to develop an inpatient fall risk adjustment model based on patient-related fall risk factors, and to analyse the impact of applying this model on comparisons of inpatient fall rates in acute care hospitals in Switzerland. METHODS Data on inpatient falls in Swiss acute care hospitals were collected on one day in 2017, 2018 and 2019, as part of an annual multicentre cross-sectional survey. After excluding maternity and outpatient wards, all inpatients older than 18 years were included. Two-level logistic regression models were used to construct unadjusted and risk-adjusted caterpillar plots to compare inter-hospital variability in inpatient fall rates. RESULTS One hundred thirty eight hospitals and 35,998 patients were included in the analysis. Risk adjustment showed that the following factors were associated with a higher risk of falling: increasing care dependency (to a great extent care dependent, odds ratio 3.43, 95% confidence interval 2.78-4.23), a fall in the last 12 months (OR 2.14, CI 1.89-2.42), the intake of sedative and or psychotropic medications (OR 1.74, CI 1.54-1.98), mental and behavioural disorders (OR 1.55, CI 1.36-1.77) and higher age (OR 1.01, CI 1.01-1.02). With odds ratios between 1.26 and 0.67, eight further ICD-10 diagnosis groups were included. Female sex (OR 0.78, CI 0.70-0.88) and postoperative patients (OR 0.83, CI 0.73-0.95) were associated with a lower risk of falling. Unadjusted caterpillar plots identified 20 low- and 3 high-performing hospitals. After risk adjustment, 2 low-performing hospitals remained. CONCLUSIONS Risk adjustment of inpatient fall rates could reduce misclassification of hospital performance and enables a fairer basis for decision-making and quality improvement measures. Patient-related fall risk factors such as care dependency, history of falls and cognitive impairment should be routinely assessed.
Collapse
Affiliation(s)
- Niklaus S Bernet
- School of Health Professions, Applied Research & Development in Nursing, Bern University of Applied Sciences, Murtenstrasse 10, 3008 Bern, Switzerland
| | - Irma HJ Everink
- Department of Health Services Research, Care and Public Health Research Institute, Maastricht University, PO BOX 616, MD 6200 Maastricht, The Netherlands
| | - Jos MGA Schols
- Department of Health Services Research, Care and Public Health Research Institute, Maastricht University, PO BOX 616, MD 6200 Maastricht, The Netherlands
| | - Ruud JG Halfens
- Department of Health Services Research, Care and Public Health Research Institute, Maastricht University, PO BOX 616, MD 6200 Maastricht, The Netherlands
| | - Dirk Richter
- School of Health Professions, Applied Research & Development in Nursing, Bern University of Applied Sciences, Murtenstrasse 10, 3008 Bern, Switzerland
- Center for Psychiatric Rehabilitation, Bern University Hospital for Mental Health, Murtenstrasse 46, 3008 Bern, Switzerland
- University Hospital for Psychiatry and Psychotherapy, University of Bern, Bolligenstrasse 111, 3060 Bern, Switzerland
| | - Sabine Hahn
- School of Health Professions, Applied Research & Development in Nursing, Bern University of Applied Sciences, Murtenstrasse 10, 3008 Bern, Switzerland
| |
Collapse
|
6
|
Buchard A, Richens JG. Artificial Intelligence for Medical Decisions. Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_28] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
7
|
Hoedl M, Eglseer D, Bernet N, Everink I, Gordon AL, Lohrmann C, Osmancevic S, Saka B, Schols JMGA, Thomann S, Bauer S. Which factors influence the prevalence of institution-acquired falls? Results from an international, multi-center, cross-sectional survey. J Nurs Scholarsh 2021; 54:462-469. [PMID: 34919335 PMCID: PMC9542022 DOI: 10.1111/jnu.12758] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 11/24/2021] [Accepted: 12/06/2021] [Indexed: 11/30/2022]
Abstract
PURPOSE Falls are a highly prevalent problem in hospitals and nursing homes with serious negative consequences such as injuries, increased care dependency, or even death. The aim of this study was to provide a comprehensive insight into institution-acquired fall (IAF) prevalence and risk factors for IAF in a large sample of hospital patients and nursing home residents among five different countries. DESIGN This study reports the outcome of a secondary data analysis of cross-sectional data collected in Austria, Switzerland, the Netherlands, Turkey, and the United Kingdom in 2017 and 2018. These data include 58,319 datapoints from hospital patients and nursing home residents. METHODS Descriptive statistics, statistical tests, logistic regression, and generalized estimating equation (GEE) models were used to analyze the data. FINDINGS IAF prevalence in hospitals and nursing homes differed significantly between the countries. Turkey (7.7%) had the highest IAF prevalence rate for hospitals, and Switzerland (15.8%) had the highest IAF prevalence rate for nursing homes. In hospitals, our model revealed that IAF prevalence was associated with country, age, care dependency, number of medical diagnoses, surgery in the last two weeks, and fall history factors. In nursing homes, care dependency, diseases of the nervous system, and fall history were identified as significant risk factors for IAF prevalence. CONCLUSIONS This large-scale study reveals that the most important IAF risk factor is an existing history of falls, independent of the setting. Whether a previous fall has occurred within the last 12 months is a simple question that should be included on every (nursing) assessment at the time of patient or resident admission. Our results guide the development of tailored prevention programs for persons at risk of falling in hospitals and nursing homes.
Collapse
Affiliation(s)
- Manuela Hoedl
- Medical University of Graz, Institute of Nursing Science, Graz, Austria
| | - Doris Eglseer
- Medical University of Graz, Institute of Nursing Science, Graz, Austria
| | - Niklaus Bernet
- Division of Nursing, Department of Health, Bern University of Applied Sciences, Bern, Switzerland
| | - Irma Everink
- Department Health Services Research, Care and Public Health Research Institute, Maastricht University, Maastricht, the Netherlands
| | - Adam L Gordon
- Division of Medical Sciences and Graduate Entry Medicine, University of Nottingham, Derby, UK.,East Midlands Academic Health Sciences Network Patient Safety Collaborative, Nottingham, UK.,NIHR Applied Research Collaboration - East Midlands (ARC-EM), Nottingham, UK
| | - Christa Lohrmann
- Medical University of Graz, Institute of Nursing Science, Graz, Austria
| | | | - Bülent Saka
- Istanbul Faculty of Medicine, Department Internal Medicine, İstanbul Tıp Fakültesi Çapa - Fatih, Istanbul University, LIstanbul, Turkey
| | - Jos M G A Schols
- Department Health Services Research, Care and Public Health Research Institute, Maastricht University, Maastricht, the Netherlands
| | - Silvia Thomann
- Division of Nursing, Department of Health, Bern University of Applied Sciences, Bern, Switzerland
| | - Silvia Bauer
- Medical University of Graz, Institute of Nursing Science, Graz, Austria
| |
Collapse
|
8
|
Wang X, Li H, Sun C, Zhang X, Wang T, Dong C, Guo D. Prediction of Mental Health in Medical Workers During COVID-19 Based on Machine Learning. Front Public Health 2021; 9:697850. [PMID: 34557468 PMCID: PMC8452905 DOI: 10.3389/fpubh.2021.697850] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2021] [Accepted: 08/16/2021] [Indexed: 01/04/2023] Open
Abstract
Mental health prediction is one of the most essential parts of reducing the probability of serious mental illness. Meanwhile, mental health prediction can provide a theoretical basis for public health department to work out psychological intervention plans for medical workers. The purpose of this paper is to predict mental health of medical workers based on machine learning by 32 factors. We collected the 32 factors of 5,108 Chinese medical workers through questionnaire survey, and the results of Self-reporting Inventory was applied to characterize mental health. In this study, we propose a novel prediction model based on optimization algorithm and neural network, which can select and rank the most important factors that affect mental health of medical workers. Besides, we use stepwise logistic regression, binary bat algorithm, hybrid improved dragonfly algorithm and the proposed prediction model to predict mental health of medical workers. The results show that the prediction accuracy of the proposed model is 92.55%, which is better than the existing algorithms. This method can be used to predict mental health of global medical worker. In addition, the method proposed in this paper can also play a role in the appropriate work plan for medical worker.
Collapse
Affiliation(s)
- Xiaofeng Wang
- Northeast Asian Research Center, Jilin University, Changchun, China
| | - Hu Li
- Northeast Asian Research Center, Jilin University, Changchun, China
| | - Chuanyong Sun
- Northeast Asian Research Center, Jilin University, Changchun, China.,Kuancheng Health Commission, Changchun, China
| | - Xiumin Zhang
- Department of Social Medicine and Health Management, School of Public Health, Jilin University, Changchun, China
| | - Tan Wang
- Northeast Asian Research Center, Jilin University, Changchun, China
| | - Chenyu Dong
- Northeast Asian Research Center, Jilin University, Changchun, China
| | - Dongyang Guo
- Northeast Asian Research Center, Jilin University, Changchun, China
| |
Collapse
|
9
|
Kaiser J, Wills N, Reilly T, Pratt J, Tumbleson V, Niemeyer M, Mindling G. A Roadmap for Practice-Based Evidence: Validation of the Hester Davis Fall Risk Scale. J Nurs Care Qual 2021; 36:223-8. [PMID: 32658000 DOI: 10.1097/NCQ.0000000000000503] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
BACKGROUND To ensure successful integration and implementation of evidence into practice, validation of measures and interventions should be performed in the population and setting in which they will be used. PURPOSE This article provides a method for evaluating the predictive performance of a risk tool using the Hester Davis fall risk tool as an example. METHODS A retrospective matched-pairs sample of fallers and nonfallers was created. Psychometric properties were calculated using 2 × 2 contingency tables and compared to data in the original report. RESULTS In this study sample, the risk tool showed minimal ability to distinguish patients at risk for falling from those not at risk. CONCLUSIONS Organizations are urged to assess the performance of risk tools in their own patient population. This article provides a practical approach for the validation of evidence into the practice setting.
Collapse
|
10
|
Ludlow K, Westbrook J, Jorgensen M, Lind KE, Baysari MT, Gray LC, Day RO, Ratcliffe J, Lord SR, Georgiou A, Braithwaite J, Raban MZ, Close J, Beattie E, Zheng WY, Debono D, Nguyen A, Siette J, Seaman K, Miao M, Root J, Roffe D, O'Toole L, Carrasco M, Thompson A, Shaikh J, Wong J, Stanton C, Haddock R. Co-designing a dashboard of predictive analytics and decision support to drive care quality and client outcomes in aged care: a mixed-method study protocol. BMJ Open 2021; 11:e048657. [PMID: 34433599 PMCID: PMC8388274 DOI: 10.1136/bmjopen-2021-048657] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
INTRODUCTION There is a clear need for improved care quality and quality monitoring in aged care. Aged care providers collect an abundance of data, yet rarely are these data integrated and transformed in real-time into actionable information to support evidence-based care, nor are they shared with older people and informal caregivers. This protocol describes the co-design and testing of a dashboard in residential aged care facilities (nursing or care homes) and community-based aged care settings (formal care provided at home or in the community). The dashboard will comprise integrated data to provide an 'at-a-glance' overview of aged care clients, indicators to identify clients at risk of fall-related hospitalisations and poor quality of life, and evidence-based decision support to minimise these risks. Longer term plans for dashboard implementation and evaluation are also outlined. METHODS This mixed-method study will involve (1) co-designing dashboard features with aged care staff, clients, informal caregivers and general practitioners (GPs), (2) integrating aged care data silos and developing risk models, and (3) testing dashboard prototypes with users. The dashboard features will be informed by direct observations of routine work, interviews, focus groups and co-design groups with users, and a community forum. Multivariable discrete time survival models will be used to develop risk indicators, using predictors from linked historical aged care and hospital data. Dashboard prototype testing will comprise interviews, focus groups and walk-through scenarios using a think-aloud approach with staff members, clients and informal caregivers, and a GP workshop. ETHICS AND DISSEMINATION This study has received ethical approval from the New South Wales (NSW) Population & Health Services Research Ethics Committee and Macquarie University's Human Research Ethics Committee. The research findings will be presented to the aged care provider who will share results with staff members, clients, residents and informal caregivers. Findings will be disseminated as peer-reviewed journal articles, policy briefs and conference presentations.
Collapse
Affiliation(s)
- Kristiana Ludlow
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
- School of Psychology, The University of Queensland, Brisbane, Queensland, Australia
| | - Johanna Westbrook
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Mikaela Jorgensen
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Kimberly E Lind
- Department of Health Promotion Sciences, Mel & Enid Zuckerman College of Public Health, The University of Arizona, Tucson, Arizona, USA
| | - Melissa T Baysari
- Discipline of Biomedical Informatics and Digital Health, Charles Perkins Centre, The University of Sydney Faculty of Medicine and Health, Sydney, New South Wales, Australia
| | - Leonard C Gray
- Centre for Research in Geriatric Medicine, The University of Queensland, Saint Lucia, Queensland, Australia
| | - Richard O Day
- St Vincent's Clinical School, University of New South Wales, Sydney, New South Wales, Australia
| | - Julie Ratcliffe
- College of Nursing and Health Sciences, Flinders University of South Australia, Adelaide, South Australia, Australia
| | - Stephen R Lord
- Neuroscience Research Australia, Sydney, New South Wales, Australia
- School of Public Health and Community Medicine, University of New South Wales, Sydney, New South Wales, Australia
| | - Andrew Georgiou
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Jeffrey Braithwaite
- Centre for Healthcare Resilience and Implementation Science, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
- The International Society for Quality in Health Care (ISQua), Dublin, Ireland
| | - Magdalena Z Raban
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Jacqueline Close
- Neuroscience Research Australia, Sydney, New South Wales, Australia
| | - Elizabeth Beattie
- School of Nursing, Queensland University of Technology, Brisbane, Queensland, Australia
| | - Wu Yi Zheng
- Black Dog Institute, Sydney, New South Wales, Australia
| | - Deborah Debono
- School of Public Health, Faculty of Health, University of Technology Sydney, Sydney, New South Wales, Australia
| | - Amy Nguyen
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
- St Vincent's Clinical School, University of New South Wales, Sydney, New South Wales, Australia
| | - Joyce Siette
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Karla Seaman
- Centre for Health Systems and Safety Research, Australian Institute of Health Innovation, Macquarie University, Sydney, New South Wales, Australia
| | - Melissa Miao
- Graduate School of Health, Faculty of Health, University of Technology Sydney, Sydney, New South Wales, Australia
| | - Jo Root
- Consumers Health Forum of Australia, Deakin, Victoria, Australia
| | - David Roffe
- IT Consultant, Sydney, New South Wales, Australia
| | - Libby O'Toole
- Aged Care Quality and Safety Commission, Sydney, New South Wales, Australia
| | | | - Alex Thompson
- Anglicare Sydney, Sydney, New South Wales, Australia
| | - Javed Shaikh
- Anglicare Sydney, Sydney, New South Wales, Australia
| | - Jeffrey Wong
- Anglicare Sydney, Sydney, New South Wales, Australia
| | - Cynthia Stanton
- Sydney North Health Network, Sydney, New South Wales, Australia
| | - Rebecca Haddock
- Deeble Institute for Health Policy Research, Australian Healthcare and Hospitals Association, Canberra, Australian Capital Territory, Australia
| |
Collapse
|
11
|
Zhu W, DeLonay A, Smith M, Carayon P, Li J. Reducing Fall-Related Revisits for Elderly Diabetes Patients in Emergency Departments: A Transition Flow Model. IEEE Robot Autom Lett 2021. [DOI: 10.1109/lra.2021.3082115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
12
|
Schultz MA, Walden RL, Cato K, Coviak CP, Cruz C, D'Agostino F, Douthit BJ, Forbes T, Gao G, Lee MA, Lekan D, Wieben A, Jeffery AD. Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review. Comput Inform Nurs 2021; 39:654-667. [PMID: 34747890 PMCID: PMC8578863 DOI: 10.1097/cin.0000000000000705] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.
Collapse
Affiliation(s)
- Mary Anne Schultz
- Author Affiliations: California State University (Dr Schultz); Annette and Irwin Eskind Family Biomedical Library, Vanderbilt University (Ms Walden); Department of Emergency Medicine, Columbia University School of Nursing (Dr Cato); Grand Valley State University (Dr Coviak); Global Health Technology & Informatics, Chevron, San Ramon, CA (Mr Cruz); Saint Camillus International University of Health Sciences, Rome, Italy (Dr D'Agostino); Duke University School of Nursing (Mr Douthit); East Carolina University College of Nursing (Dr Forbes); St Catherine University Department of Nursing (Dr Gao); Texas Woman's University College of Nursing (Dr Lee); Assistant Professor, University of North Carolina at Greensboro School of Nursing (Dr Lekan); University of Wisconsin School of Nursing (Ms Wieben); and Vanderbilt University School of Nursing, and Tennessee Valley Healthcare System, US Department of Veterans Affairs (Dr Jeffery)
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
13
|
Loresto FL Jr, Grant C, Solberg J, Eron K. Assessing the Effect of Unit Champion-Initiated Audits on Fall Rates: Improving Awareness. J Nurs Care Qual 2020; 35:227-32. [PMID: 32433145 DOI: 10.1097/NCQ.0000000000000449] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
BACKGROUND Inpatient falls remain challenging with repercussions that can include patient injury and increased hospital expense. Fall rates were consistently above the national benchmark. An initiative to reduce fall rates was use of Fall Champion Audits (FCAs). PURPOSE The aim of this study was to assess the effect of FCAs on patient fall rates. METHODS FCAs were piloted on a medical-oncology unit. An interrupted time series design was used to assess the effect of FCAs on fall rates. INTERVENTION FCA is an audit conducted by the unit fall champion that assesses fall risk, interventions, and barriers among staff and patients. RESULTS Analysis suggested a significant decrease in fall rates from pre- (3.75) to postimplementation (1.62). FCAs worked in conjunction with a division-wide fall program in reducing fall rate. CONCLUSIONS FCAs, in conjunction with a fall program, are a feasible intervention in reducing fall rates.
Collapse
|
14
|
Buchard A, Richens JG. Artificial Intelligence for Medical Decisions. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_28-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
15
|
Lindberg DS, Prosperi M, Bjarnadottir RI, Thomas J, Crane M, Chen Z, Shear K, Solberg LM, Snigurska UA, Wu Y, Xia Y, Lucero RJ. Identification of important factors in an inpatient fall risk prediction model to improve the quality of care using EHR and electronic administrative data: A machine-learning approach. Int J Med Inform 2020; 143:104272. [PMID: 32980667 PMCID: PMC8562928 DOI: 10.1016/j.ijmedinf.2020.104272] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2020] [Revised: 07/03/2020] [Accepted: 09/10/2020] [Indexed: 12/02/2022]
Abstract
BACKGROUND Inpatient falls, many resulting in injury or death, are a serious problem in hospital settings. Existing falls risk assessment tools, such as the Morse Fall Scale, give a risk score based on a set of factors, but don't necessarily signal which factors are most important for predicting falls. Artificial intelligence (AI) methods provide an opportunity to improve predictive performance while also identifying the most important risk factors associated with hospital-acquired falls. We can glean insight into these risk factors by applying classification tree, bagging, random forest, and adaptive boosting methods applied to Electronic Health Record (EHR) data. OBJECTIVE The purpose of this study was to use tree-based machine learning methods to determine the most important predictors of inpatient falls, while also validating each via cross-validation. MATERIALS AND METHODS A case-control study was designed using EHR and electronic administrative data collected between January 1, 2013 to October 31, 2013 in 14 medical surgical units. The data contained 38 predictor variables which comprised of patient characteristics, admission information, assessment information, clinical data, and organizational characteristics. Classification tree, bagging, random forest, and adaptive boosting methods were used to identify the most important factors of inpatient fall-risk through variable importance measures. Sensitivity, specificity, and area under the ROC curve were computed via ten-fold cross validation and compared via pairwise t-tests. These methods were also compared to a univariate logistic regression of the Morse Fall Scale total score. RESULTS In terms of AUROC, bagging (0.89), random forest (0.90), and boosting (0.89) all outperformed the Morse Fall Scale (0.86) and the classification tree (0.85), but no differences were measured between bagging, random forest, and adaptive boosting, at a p-value of 0.05. History of Falls, Age, Morse Fall Scale total score, quality of gait, unit type, mental status, and number of high fall risk increasing drugs (FRIDs) were considered the most important features for predicting inpatient fall risk. CONCLUSIONS Machine learning methods have the potential to identify the most relevant and novel factors for the detection of hospitalized patients at risk of falling, which would improve the quality of patient care, and to more fully support healthcare provider and organizational leadership decision-making. Nurses would be able to enhance their judgement to caring for patients at risk for falls. Our study may also serve as a reference for the development of AI-based prediction models of other iatrogenic conditions. To our knowledge, this is the first study to report the importance of patient, clinical, and organizational features based on the use of AI approaches.
Collapse
Affiliation(s)
- David S Lindberg
- Department of Statistics, College of Liberal Arts and Sciences, University of Florida, United States.
| | - Mattia Prosperi
- Department of Epidemiology, College of Public Health and Health Professions and College of Medicine, University of Florida, United States
| | - Ragnhildur I Bjarnadottir
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States
| | | | | | - Zhaoyi Chen
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, United States
| | - Kristen Shear
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States
| | - Laurence M Solberg
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States; NF/SG VAHS, Geriatrics Research, Education, and Clinical Center (GRECC) Gainesville, Florida, United States
| | - Urszula Alina Snigurska
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States
| | - Yonghui Wu
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, United States
| | - Yunpeng Xia
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States
| | - Robert J Lucero
- Department of Family, Community, and Health Systems Science, College of Nursing, University of Florida, United States
| |
Collapse
|
16
|
Scheidenhelm S, Astroth KS, DeLong K, Starkey C, Wolfe D. Retrospective Analysis of Factors Associated With a Revised Fall Prevention Bundle in Hospitalized Patients. J Nurs Adm 2020; 50:571-7. [PMID: 33105333 DOI: 10.1097/NNA.0000000000000939] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
OBJECTIVE The study aims to describe factors associated and injuries sustained with inpatients who fell while hospitalized and identify the impact of a revised fall-prevention bundle. BACKGROUND Approximately 1 million falls occur in hospitals annually, accounting for approximately 70% of inpatient accidents. Inpatient falls can result in physical injury, increased patient mortality and morbidity, decreased quality of life, and increased length of stay and cost. METHODS We used a retrospective review of patient fall data for adult inpatients who fell while hospitalized. RESULTS After reeducation and implementation of all elements of a revised fall-prevention bundle, there were fewer falls per patient day. We identified additional characteristics indicating when patients were more likely to be injured in a fall. CONCLUSIONS A fall-prevention bundle is effective in decreasing inpatient falls and falls with injury. Raising awareness of additional factors may decrease risk of injuries during an inpatient fall.
Collapse
|
17
|
Rundo L, Pirrone R, Vitabile S, Sala E, Gambino O. Recent advances of HCI in decision-making tasks for optimized clinical workflows and precision medicine. J Biomed Inform 2020; 108:103479. [DOI: 10.1016/j.jbi.2020.103479] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2020] [Revised: 04/27/2020] [Accepted: 06/06/2020] [Indexed: 12/28/2022]
|
18
|
Prosperi M, Guo Y, Sperrin M, Koopman JS, Min JS, He X, Rich S, Wang M, Buchan IE, Bian J. Causal inference and counterfactual prediction in machine learning for actionable healthcare. NAT MACH INTELL 2020; 2:369-75. [DOI: 10.1038/s42256-020-0197-y] [Citation(s) in RCA: 68] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|