Decision analysis framework for predicting no-shows to appointments using machine learning algorithms

BACKGROUND

No-show to medical appointments has significant adverse effects on healthcare systems and their clients. Using machine learning to predict no-shows allows managers to implement strategies such as overbooking and reminders targeting patients most likely to miss appointments, optimizing the use of resources.

METHODS

In this study, we proposed a detailed analytical framework for predicting no-shows while addressing imbalanced datasets. The framework includes a novel use of z-fold cross-validation performed twice during the modeling process to improve model robustness and generalization. We also introduce Symbolic Regression (SR) as a classification algorithm and Instance Hardness Threshold (IHT) as a resampling technique and compared their performance with that of other classification algorithms, such as K-Nearest Neighbors (KNN) and Support Vector Machine (SVM), and resampling techniques, such as Random under Sampling (RUS), Synthetic Minority Oversampling Technique (SMOTE) and NearMiss-1. We validated the framework using two attendance datasets from Brazilian hospitals with no-show rates of 6.65% and 19.03%.

RESULTS

From the academic perspective, our study is the first to propose using SR and IHT to predict the no-show of patients. Our findings indicate that SR and IHT presented superior performances compared to other techniques, particularly IHT, which excelled when combined with all classification algorithms and led to low variability in performance metrics results. Our results also outperformed sensitivity outcomes reported in the literature, with values above 0.94 for both datasets.

CONCLUSION

This is the first study to use SR and IHT methods to predict patient no-shows and the first to propose performing z-fold cross-validation twice. Our study highlights the importance of avoiding relying on few validation runs for imbalanced datasets as it may lead to biased results and inadequate analysis of the generalization and stability of the models obtained during the training stage.

Digital technologies: An exploratory study of their role in the resilience of healthcare services

Descriptions of resilient performance in healthcare services usually emphasize the role of skills and knowledge of caregivers. At the same time, the human factors discipline often frames digital technologies as sources of brittleness. This paper presents an exploratory investigation of the upside of ten digital technologies derived from Healthcare 4.0 (H4.0) in terms of their perceived contribution to six healthcare services and the four abilities of resilient healthcare: monitor, anticipate, respond, and learn. This contribution was assessed through a multinational survey conducted with 109 experts. Emergency rooms (ERs) and intensive care units (ICUs) stood out as the most benefited by H4.0 technologies. That is consistent with the high complexity of those services, which demand resilient performance. Four H4.0 technologies were top ranked regarding their impacts on the resilience of those services. They are further explored in follow-up interviews with ER and ICU professionals from hospitals in emerging and developed economies to collect examples of applications in their routines.

Forecasting the length-of-stay of pediatric patients in hospitals: a scoping review

BACKGROUND

Healthcare management faces complex challenges in allocating hospital resources, and predicting patients' length-of-stay (LOS) is critical in effectively managing those resources. This work aims to map approaches used to forecast the LOS of Pediatric Patients in Hospitals (LOS-P) and patients' populations and environments used to develop the models.

METHODS

Using the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) methodology, we performed a scoping review that identified 28 studies and analyzed them. The search was conducted on four databases (Science Direct, Scopus, Web of Science, and Medline). The identification of relevant studies was structured around three axes related to the research questions: (i) forecast models, (ii) hospital length-of-stay, and (iii) pediatric patients. Two authors carried out all stages to ensure the reliability of the review process. Articles that passed the initial screening had their data charted on a spreadsheet. Methods reported in the literature were classified according to the stage in which they are used in the modeling process: (i) pre-processing of data, (ii) variable selection, and (iii) cross-validation.

RESULTS

Forecasting models are most often applied to newborn patients and, consequently, in neonatal intensive care units. Regression analysis is the most widely used modeling approach; techniques associated with Machine Learning are still incipient and primarily used in emergency departments to model patients in specific situations.

CONCLUSIONS

The studies' main benefits include informing family members about the patient's expected discharge date and enabling hospital resources' allocation and planning. Main research gaps are associated with the lack of generalization of forecasting models and limited reported applicability in hospital management. This study also provides a practical guide to LOS-P forecasting methods and a future research agenda.

Contributions of Industry 4.0 to supply chain resilience

Purpose

This study aims at identifying the contribution of Industry 4.0 (I4.0) integration into supply chains (SCs) to the enhancement of SC resilience.

Design/methodology/approach

A scoping review was conducted so that the relevant literature on SC resilience, and I4.0 integrated into SC management was examined.

Findings

The authors summarize the main findings from existing research and propose three research directions: (1) empirical validation of the contribution of I4.0 ICTs to SC resilience; (2) explore the role of processing-actuation technologies in enhancing restorative capacity; and (3) integration between I4.0 ICTs and omni-channel strategy as a means to resilience development at consumer and retail levels. The literature on the design of resilient smart SCs is far outnumbered by works reporting applications of I4.0 ICTs at different SC tier levels. However, the authors’ scoping review organizes the information available on these themes, setting the ground for the development of new theoretical propositions.

Originality/value

The integration of digital technologies from I4.0 can fundamentally change the SC management, acting as enablers of a more effective response to disruptions. However, the digital transformation of SCs is still incipient, and literature is particularly sparse when considering the contribution of I4.0 to the resilience of SCs.

Development and Validation of a Predictive Model of Success in Bariatric Surgery

PURPOSE

There are no criteria to establish priority for bariatric surgery candidates in the public health system in several countries. The aim of this study is to identify preoperative characteristics that allow predicting the success after bariatric surgery.

MATERIALS AND METHODS

Four hundred and sixty-one patients submitted to Roux-en-Y gastric bypass were included. Success of the surgery was defined as the sum of five outcome variables, assessed at baseline and 12 months after the surgery: excess weight loss, use of continuous positive airway pressure (CPAP) or bilevel positive airway pressure (BiPAP) as a treatment for obstructive sleep apnea (OSA), daily number of antidiabetics, daily number of antihypertensive drugs, and all-cause mortality. Partial least squares (PLS) regression and multiple linear regression were performed to identify preoperative predictors. We performed a 90/10 split of the dataset in train and test sets and ran a leave-one-out cross-validation on the train set and the best PLS model was chosen based on goodness-of-fit criteria.

RESULTS

The preoperative predictors of success after bariatric surgery included lower age, presence of non-alcoholic fatty liver disease and OSA, more years of CPAP/BiPAP use, negative history of cardiovascular disease, and lower number of antihypertensive drugs. The PLS model displayed a mean absolute percent error of 0.1121 in the test portion of the dataset, leading to accurate predictions of postoperative outcomes.

CONCLUSION

This success index allows prioritizing patients with the best indication for the procedure and could be incorporated in the public health system as a support tool in the decision-making process.

Surgery scheduling heuristic considering OR downstream and upstream facilities and resources

BACKGROUND

Surgical theater (ST) operations planning is a key subject in the healthcare management literature, particularly the scheduling of procedures in operating rooms (ORs). The OR scheduling problem is usually approached using mathematical modeling and made available to ST managers through dedicated software. Regardless of the large body of knowledge on the subject, OR scheduling models rarely consider the integration of OR downstream and upstream facilities and resources or validate their propositions in real life, rather using simulated scenarios. We propose a heuristic to sequence surgeries that considers both upstream and downstream resources required to perform them, such as surgical kits, post anesthesia care unit (PACU) beds, and surgical teams (surgeons, nurses and anesthetists).

METHODS

Using hybrid flow shop (HFS) techniques and the break-in-moment (BIM) concept, the goal is to find a sequence that maximizes the number of procedures assigned to the ORs while minimizing the variance of intervals between surgeries' completions, smoothing the demand for downstream resources such as PACU beds and OR sanitizing teams. There are five steps to the proposed heuristic: listing of priorities, local scheduling, global scheduling, feasibility check and identification of best scheduling.

RESULTS

Our propositions were validated in a high complexity tertiary University hospital in two ways: first, applying the heuristic to historical data from five typical ST days and comparing the performance of our proposed sequences to the ones actually implemented; second, pilot testing the heuristic during ten days in the ORs, allowing a full rotation of surgical specialties. Results displayed an average increase of 37.2% in OR occupancy, allowing an average increase of 4.5 in the number of surgeries performed daily, and reducing the variance of intervals between surgeries' completions by 55.5%. A more uniform distribution of patients' arrivals at the PACU was also observed.

CONCLUSIONS

Our proposed heuristic is particularly useful to plan the operation of STs in which resources are constrained, a situation that is common in hospital from developing countries. Our propositions were validated through a pilot implementation in a large hospital, contributing to the scarce literature on actual OR scheduling implementation.

Decision Support for Breast Cancer Detection: Classification Improvement Through Feature Selection

Several statistical-based approaches have been developed to support medical personnel in early breast cancer detection. This article presents a method for feature selection aimed at classifying cases into categories based on patients' breast tissue measures and protein microarray. The effectiveness of this feature selection strategy was evaluated against the commonly used Wisconsin Breast Cancer Database-WBCD (with several patients and fewer features) and a new protein microarray data set (with several features and fewer patients). Features were ranked according to a feature importance index that combines parameters emerging from the unsupervised method of principal component analysis and the supervised method of Bhattacharyya distance. Observations of a training set were iteratively categorized into malignant and benign cases through 3 classification techniques: k-Nearest Neighbor, linear discriminant analysis, and probabilistic neural network. After each classification, the feature with the smallest importance index was removed, and a new categorization was carried out until there was only one feature left. The subset yielding maximum accuracy was used to classify observations in the testing set. Our method yielded average 99.17% accurate classifications in the testing set while retaining average 4.61 out of 9 features in the WBCD, which is comparable to the best results reported by the literature on that data set, with the advantage of relying on simple and widely available multivariate techniques. When applied to the microarray data, the method yielded average accuracy of 98.30% while retaining average 2.17% of the original features. Our results can aid health-care professionals during early diagnosis of breast cancer.

Predicting the occurrence of surgical site infections using text mining and machine learning

In this study we propose the use of text mining and machine learning methods to predict and detect Surgical Site Infections (SSIs) using textual descriptions of surgeries and post-operative patients’ records, mined from the database of a high complexity University hospital. SSIs are among the most common adverse events experienced by hospitalized patients; preventing such events is fundamental to ensure patients’ safety. Knowledge on SSI occurrence rates may also be useful in preventing future episodes. We analyzed 15,479 surgery descriptions and post-operative records testing different preprocessing strategies and the following machine learning algorithms: Linear SVC, Logistic Regression, Multinomial Naive Bayes, Nearest Centroid, Random Forest, Stochastic Gradient Descent, and Support Vector Classification (SVC). For prediction purposes, the best result was obtained using the Stochastic Gradient Descent method (79.7% ROC-AUC); for detection, Logistic Regression yielded the best performance (80.6% ROC-AUC).

Enhancing counterfeit and illicit medicines grouping via feature selection and X-ray fluorescence spectrometry

In this paper, we propose a novel framework to select the most relevant X-Ray Fluorescence (XRF) energy values (i.e., features) to enhance the clustering (grouping) of counterfeit and illicit medical tablets. The framework is based on the integration of multidimensional scaling (MDS) and Procrustes analysis (PA) multivariate techniques. MDS provides a projection of the original data into a lower dimension, while PA finds a projection matrix from the original data. Such outputs give rise to a feature importance index that guides an iterative feature selection process; after each feature is inserted in the subset, an optimization procedure based on a greedy search method is carried out to maximize the clustering quality assessed through the Silhouette Index (SI). The inorganic chemical fingerprinting of 41 commercial samples (Viagra®, Cialis®, Lazar®, Libiden®, Maxfil®, Plenovit®, Potent 75®, Rigix®, V-50®, Vimax® and Pramil®) and 56 seized counterfeit samples (Viagra and Cialis) was used to validate the proposed framework. From the original 2048 data points in the full spectra, we identified a subset comprised of 41 energy values that substantially improved clustering quality; the obtained groups were assessed by visual inspection of the PCA plots.

Layout Planning in Healthcare Facilities: A Systematic Review

This study presents a systematic review of the literature on layout planning in healthcare facilities. The review includes 81 articles from journals, conferences, books, and other documents. Articles were classified in two groups according to their main contents including (i) concepts and guidelines and (ii) techniques and tools to assist in layout planning in healthcare facilities. Results indicate that a great variety of concepts and tools have been used to solve layout problems in healthcare. However, healthcare environments such as hospitals can be complex, limiting the ability to obtain optimal layout solutions. Influential factors may include the flows of patients, staff, materials, and information; layout planning and implementation costs; staff and patients safety and well-being; and environmental contamination, among others. The articles reviewed discussed and often proposed solutions covering one or more factors. Results helped us to propose future research directions on the subject.

Simulating the behavior of patients who leave a public hospital emergency department without being seen by a physician: a cellular automaton and agent-based framework

The objective of this study was to develop an agent based modeling (ABM) framework to simulate the behavior of patients who leave a public hospital emergency department (ED) without being seen (LWBS). In doing so, the study complements computer modeling and cellular automata (CA) techniques to simulate the behavior of patients in an ED. After verifying and validating the model by comparing it with data from a real case study, the significance of four preventive policies including increasing number of triage nurses, fast-track treatment, increasing the waiting room capacity and reducing treatment time were investigated by utilizing ordinary least squares regression. After applying the preventing policies in ED, an average of 42.14% reduction in the number of patients who leave without being seen and 6.05% reduction in the average length of stay (LOS) of patients was reported. This study is the first to apply CA in an ED simulation. Comparing the average LOS before and after applying CA with actual times from emergency department information system showed an 11% improvement. The simulation results indicated that the most effective approach to reduce the rate of LWBS is applying fast-track treatment. The ABM approach represents a flexible tool that can be constructed to reflect any given environment. It is also a support system for decision-makers to assess the relative impact of control strategies.

Text mining approach to predict hospital admissions using early medical records from the emergency department

OBJECTIVE

Emergency department (ED) overcrowding is a serious issue for hospitals. Early information on short-term inward bed demand from patients receiving care at the ED may reduce the overcrowding problem, and optimize the use of hospital resources. In this study, we use text mining methods to process data from early ED patient records using the SOAP framework, and predict future hospitalizations and discharges.

DESIGN

We try different approaches for pre-processing of text records and to predict hospitalization. Sets-of-words are obtained via binary representation, term frequency, and term frequency-inverse document frequency. Unigrams, bigrams and trigrams are tested for feature formation. Feature selection is based on χ² and F-score metrics. In the prediction module, eight text mining methods are tested: Decision Tree, Random Forest, Extremely Randomized Tree, AdaBoost, Logistic Regression, Multinomial Naïve Bayes, Support Vector Machine (Kernel linear) and Nu-Support Vector Machine (Kernel linear).

MEASUREMENTS

Prediction performance is evaluated by F1-scores. Precision and Recall values are also informed for all text mining methods tested.

RESULTS

Nu-Support Vector Machine was the text mining method with the best overall performance. Its average F1-score in predicting hospitalization was 77.70%, with a standard deviation (SD) of 0.66%.

CONCLUSIONS

The method could be used to manage daily routines in EDs such as capacity planning and resource allocation. Text mining could provide valuable information and facilitate decision-making by inward bed management teams.

Forecasting Daily Volume and Acuity of Patients in the Emergency Department

This study aimed at analyzing the performance of four forecasting models in predicting the demand for medical care in terms of daily visits in an emergency department (ED) that handles high complexity cases, testing the influence of climatic and calendrical factors on demand behavior. We tested different mathematical models to forecast ED daily visits at Hospital de Clínicas de Porto Alegre (HCPA), which is a tertiary care teaching hospital located in Southern Brazil. Model accuracy was evaluated using mean absolute percentage error (MAPE), considering forecasting horizons of 1, 7, 14, 21, and 30 days. The demand time series was stratified according to patient classification using the Manchester Triage System's (MTS) criteria. Models tested were the simple seasonal exponential smoothing (SS), seasonal multiplicative Holt-Winters (SMHW), seasonal autoregressive integrated moving average (SARIMA), and multivariate autoregressive integrated moving average (MSARIMA). Performance of models varied according to patient classification, such that SS was the best choice when all types of patients were jointly considered, and SARIMA was the most accurate for modeling demands of very urgent (VU) and urgent (U) patients. The MSARIMA models taking into account climatic factors did not improve the performance of the SARIMA models, independent of patient classification.

Programação de tarefas baseada em curvas de aprendizado para linhas de produção customizadas

A manufatura de produtos personalizados, também conhecida como customização em massa, implica no aumento da variedade de modelos e demanda redução no tamanho dos lotes de produção. Tarefas que dependem da habilidade humana são especialmente afetadas nesse contexto, visto que os trabalhadores precisam se adaptar às características do novo modelo. Esse processo de adaptação dificulta a operacionalização de técnicas de programação de tarefas, uma vez que o tempo de processamento da tarefa é de difícil determinação. Este artigo integra informações oriundas da modelagem de curvas de aprendizado a heurísticas de programação de tarefas voltadas à minimização do tempo demandado para término de um conjunto de tarefas. O tempo de processamento de lotes (tarefas) com diferentes tamanhos e graus de complexidade é estimado através de curvas de aprendizado, sendo então utilizado em heurísticas para programação de tarefas em equipes de trabalhadores paralelos não relacionados. A heurística recomendada, identificada através de simulação, apresenta um desvio de 4,9% em relação ao tempo de término da sequência ótima de tarefas e conduz a um nível satisfatório de ocupação entre as equipes. A heurística é aplicada em um processo da indústria calçadista