Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach

Healthcare systems face significant challenges and financial burdens due to patient no-shows, highlighting the need for accurate and interpretable predictive models. This study evaluated the efficacy of twelve classification algorithms that can generate self-explanatory results illustrations across...

Full description

Saved in:
Bibliographic Details
Main Authors: Khaled M. Toffaha, Mecit Can Emre Simsekler, Aamna Alshehhi, Mohammed Atif Omar
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10741524/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846163870072176640
author Khaled M. Toffaha
Mecit Can Emre Simsekler
Aamna Alshehhi
Mohammed Atif Omar
author_facet Khaled M. Toffaha
Mecit Can Emre Simsekler
Aamna Alshehhi
Mohammed Atif Omar
author_sort Khaled M. Toffaha
collection DOAJ
description Healthcare systems face significant challenges and financial burdens due to patient no-shows, highlighting the need for accurate and interpretable predictive models. This study evaluated the efficacy of twelve classification algorithms that can generate self-explanatory results illustrations across four categories: Rule Set classifiers, Rule List classifiers, Rule Tree classifiers, and Algebraic Models, using a real-world dataset, “Brazilian Medical Appointment No Shows”. Analysis across multiple performance metrics revealed significant differences among the algorithms. Advanced models like Tree- Generalized Additive Model (GAM), Fast Interpretable Greedy-Tree Sums (FIGS), Tree Alternating Optimization (TAO) Tree, and RuleFit demonstrated superior predictive capabilities using Over-Sampling and feature selection, achieving an accuracy of 87.53%, AUC 0.87, and F1-score of 0.86, compared to basic tree algorithms like Greedy Tree and C4.5. While Tree-GAM showed high accuracy, it had a significantly longer runtime of approximately 101 seconds. FIGS and TAO Tree offered compelling alternatives with comparable accuracy but significantly reduced computational demands, with runtimes under 1 second. These findings highlight the trade-offs between predictive power, computational efficiency, and practical implementation in healthcare settings. The study also revealed the value of flexible, adaptive architectures in capturing nuanced factors influencing patient no-shows. Overall, these advanced algorithms present accurate and interpretable solutions for forecasting patient no-shows, with FIGS and TAO Tree emerging as particularly effective choices that offer a good balance between predictive insight and practical viability. These insights aim to guide health systems in optimizing patient access and reliability while addressing the complex issue of no-shows, underscoring the importance of considering multiple performance metrics when selecting algorithms for real-world applications.
format Article
id doaj-art-dc5a5434576b41cab859b0f2aed9ffc4
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-dc5a5434576b41cab859b0f2aed9ffc42024-11-19T00:01:10ZengIEEEIEEE Access2169-35362024-01-011216605816606710.1109/ACCESS.2024.349066210741524Predicting Hospital No-Shows: Interpretable Machine Learning Models ApproachKhaled M. Toffaha0https://orcid.org/0000-0002-7765-5430Mecit Can Emre Simsekler1https://orcid.org/0000-0002-1555-5012Aamna Alshehhi2https://orcid.org/0000-0003-1868-1003Mohammed Atif Omar3https://orcid.org/0000-0001-8833-2947Department of Management Science and Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesDepartment of Management Science and Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesDepartment of Biomedical Engineering and Biotechnology, Khalifa University, Abu Dhabi, United Arab EmiratesDepartment of Management Science and Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesHealthcare systems face significant challenges and financial burdens due to patient no-shows, highlighting the need for accurate and interpretable predictive models. This study evaluated the efficacy of twelve classification algorithms that can generate self-explanatory results illustrations across four categories: Rule Set classifiers, Rule List classifiers, Rule Tree classifiers, and Algebraic Models, using a real-world dataset, “Brazilian Medical Appointment No Shows”. Analysis across multiple performance metrics revealed significant differences among the algorithms. Advanced models like Tree- Generalized Additive Model (GAM), Fast Interpretable Greedy-Tree Sums (FIGS), Tree Alternating Optimization (TAO) Tree, and RuleFit demonstrated superior predictive capabilities using Over-Sampling and feature selection, achieving an accuracy of 87.53%, AUC 0.87, and F1-score of 0.86, compared to basic tree algorithms like Greedy Tree and C4.5. While Tree-GAM showed high accuracy, it had a significantly longer runtime of approximately 101 seconds. FIGS and TAO Tree offered compelling alternatives with comparable accuracy but significantly reduced computational demands, with runtimes under 1 second. These findings highlight the trade-offs between predictive power, computational efficiency, and practical implementation in healthcare settings. The study also revealed the value of flexible, adaptive architectures in capturing nuanced factors influencing patient no-shows. Overall, these advanced algorithms present accurate and interpretable solutions for forecasting patient no-shows, with FIGS and TAO Tree emerging as particularly effective choices that offer a good balance between predictive insight and practical viability. These insights aim to guide health systems in optimizing patient access and reliability while addressing the complex issue of no-shows, underscoring the importance of considering multiple performance metrics when selecting algorithms for real-world applications.https://ieeexplore.ieee.org/document/10741524/Patient no-showsdecision tree algorithmsgreedy tree classifiersadditive model treeshierarchical shrinkage treeshealthcare analytics
spellingShingle Khaled M. Toffaha
Mecit Can Emre Simsekler
Aamna Alshehhi
Mohammed Atif Omar
Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
IEEE Access
Patient no-shows
decision tree algorithms
greedy tree classifiers
additive model trees
hierarchical shrinkage trees
healthcare analytics
title Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
title_full Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
title_fullStr Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
title_full_unstemmed Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
title_short Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach
title_sort predicting hospital no shows interpretable machine learning models approach
topic Patient no-shows
decision tree algorithms
greedy tree classifiers
additive model trees
hierarchical shrinkage trees
healthcare analytics
url https://ieeexplore.ieee.org/document/10741524/
work_keys_str_mv AT khaledmtoffaha predictinghospitalnoshowsinterpretablemachinelearningmodelsapproach
AT mecitcanemresimsekler predictinghospitalnoshowsinterpretablemachinelearningmodelsapproach
AT aamnaalshehhi predictinghospitalnoshowsinterpretablemachinelearningmodelsapproach
AT mohammedatifomar predictinghospitalnoshowsinterpretablemachinelearningmodelsapproach