Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study
Abstract BackgroundPatients with heart failure frequently face the possibility of rehospitalization following an initial hospital stay, placing a significant burden on both patients and health care systems. Accurate predictive tools are crucial for guiding clinical decision-ma...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-12-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2024/1/e58812 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555933825597440 |
|---|---|
| author | Xiangkui Jiang Bingquan Wang |
| author_facet | Xiangkui Jiang Bingquan Wang |
| author_sort | Xiangkui Jiang |
| collection | DOAJ |
| description |
Abstract
BackgroundPatients with heart failure frequently face the possibility of rehospitalization following an initial hospital stay, placing a significant burden on both patients and health care systems. Accurate predictive tools are crucial for guiding clinical decision-making and optimizing patient care. However, the effectiveness of existing models tailored specifically to the Chinese population is still limited.
ObjectiveThis study aimed to formulate a predictive model for assessing the likelihood of readmission among patients diagnosed with heart failure.
MethodsIn this study, we analyzed data from 1948 patients with heart failure in a hospital in Sichuan Province between 2016 and 2019. By applying 3 variable selection strategies, 29 relevant variables were identified. Subsequently, we constructed 6 predictive models using different algorithms: logistic regression, support vector machine, gradient boosting machine, Extreme Gradient Boosting, multilayer perception, and graph convolutional networks.
ResultsThe graph convolutional network model showed the highest prediction accuracy with an area under the receiver operating characteristic curve of 0.831, accuracy of 75%, sensitivity of 52.12%, and specificity of 90.25%.
ConclusionsThe model crafted in this study proves its effectiveness in forecasting the likelihood of readmission among patients with heart failure, thus serving as a crucial reference for clinical decision-making. |
| format | Article |
| id | doaj-art-d5100d6692264da594b33e0025e36283 |
| institution | Kabale University |
| issn | 2291-9694 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj-art-d5100d6692264da594b33e0025e362832025-01-07T20:31:32ZengJMIR PublicationsJMIR Medical Informatics2291-96942024-12-0112e58812e5881210.2196/58812Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development StudyXiangkui Jianghttp://orcid.org/0000-0002-7245-770XBingquan Wanghttp://orcid.org/0009-0004-4382-8198 Abstract BackgroundPatients with heart failure frequently face the possibility of rehospitalization following an initial hospital stay, placing a significant burden on both patients and health care systems. Accurate predictive tools are crucial for guiding clinical decision-making and optimizing patient care. However, the effectiveness of existing models tailored specifically to the Chinese population is still limited. ObjectiveThis study aimed to formulate a predictive model for assessing the likelihood of readmission among patients diagnosed with heart failure. MethodsIn this study, we analyzed data from 1948 patients with heart failure in a hospital in Sichuan Province between 2016 and 2019. By applying 3 variable selection strategies, 29 relevant variables were identified. Subsequently, we constructed 6 predictive models using different algorithms: logistic regression, support vector machine, gradient boosting machine, Extreme Gradient Boosting, multilayer perception, and graph convolutional networks. ResultsThe graph convolutional network model showed the highest prediction accuracy with an area under the receiver operating characteristic curve of 0.831, accuracy of 75%, sensitivity of 52.12%, and specificity of 90.25%. ConclusionsThe model crafted in this study proves its effectiveness in forecasting the likelihood of readmission among patients with heart failure, thus serving as a crucial reference for clinical decision-making.https://medinform.jmir.org/2024/1/e58812 |
| spellingShingle | Xiangkui Jiang Bingquan Wang Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study JMIR Medical Informatics |
| title | Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study |
| title_full | Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study |
| title_fullStr | Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study |
| title_full_unstemmed | Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study |
| title_short | Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study |
| title_sort | enhancing clinical decision making by predicting readmission risk in patients with heart failure using machine learning predictive model development study |
| url | https://medinform.jmir.org/2024/1/e58812 |
| work_keys_str_mv | AT xiangkuijiang enhancingclinicaldecisionmakingbypredictingreadmissionriskinpatientswithheartfailureusingmachinelearningpredictivemodeldevelopmentstudy AT bingquanwang enhancingclinicaldecisionmakingbypredictingreadmissionriskinpatientswithheartfailureusingmachinelearningpredictivemodeldevelopmentstudy |