Key result
Machine learning modestly edges logistic regression in predicting 30-day readmissions by an AUC of ~0.03.
Why the study?
Machine learning algorithms are increasingly used for predicting hospital readmissions, prompting an evaluation of their performance compared with logistic regression for predicting 30-day hospital readmissions among US patients.
Do machine learning algorithms improve the prediction of 30-day hospital readmissions compared to logistic regression in US adults?
Meta-Analysis (n=9)
Do machine learning algorithms improve the prediction of 30-day hospital readmissions compared to logistic regression in US adults?
Mean Difference: 0.03 (95% CI 0.01–0.05)
Machine learning models, particularly deep learning, offer a modest improvement over traditional logistic regression in predicting 30-day hospital readmissions.
Modest AUC gains warrant no practice change in readmission prediction; extends comparative evidence but requires prospective validation.
Machine learning algorithms are being increasingly used for predicting hospital readmissions. This meta-analysis evaluated the performance of logistic regression (LR) and machine learning (ML) models for the prediction of 30-day hospital readmission among patients in the US. Electronic databases (i.e., Medline, PubMed, and Embase) were searched from January 2015 to December 2019. Only studies in the English language were included. Two reviewers performed studies screening, quality appraisal, and data collection. The quality of the studies was assessed using the Quality in Prognosis Studies (QUIPS) tool. Model performance was evaluated using the Area Under Curve (AUC). A random-effects meta-analysis was performed using STATA 16.0MP. Nine studies were included based on the selection criteria. The most common ML methods applied were deep learning methods, classification trees, and artificial neural networks. Most of the studies had a low risk of bias (8/9). The AUC was greater with ML to predict 30-day all-cause hospital readmission compared with LR [Mean Difference (MD): 0.03; 95% Confidence Interval (CI) 0.01–0.05]. After sensitivity analysis, deep-learning methods had better performance compared with LR (MD 0.06; 95% CI, 0.04–0.09), followed by neuron networks (MD: 0.03; 95% CI, 0.03–0.03), while the AUCs of the tree-based (MD: 0.02; 95% CI -0.00-0.04) and kernel-based (MD: 0.02; 95% CI 0.02 (−0.13–0.16) methods were no different compared with LR. More than half of the studies evaluated heart failure-related rehospitalization (N = 5). For the readmission prediction among heart failure patients, ML performed better compared with LR, with a mean difference in AUC of 0.04 (95% CI, 0.01–0.07). The leave-one-out sensitivity analysis confirmed the robustness of the findings. Multiple ML methods were used to predict 30-day all-cause hospital readmission. Performance varied across the ML methods, with deep-learning methods showing the best performance over the LR.
No takes yet. Share an insight, caveat, or question.
Talwar et al. (2023) conducted a meta-analysis in 30-day hospital readmission (n=9). Machine learning algorithms vs. Logistic regression was evaluated on Area Under Curve (AUC) for predicting 30-day all-cause hospital readmission (MD 0.03, 95% CI 0.01-0.05). Machine learning algorithms demonstrated a modestly greater Area Under the Curve compared to logistic regression for predicting 30-day all-cause hospital readmissions (MD 0.03).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: