Comparison of machine learning algorithms in predicting hospital readmissions for diabetic patients

Shefqet Meda (), Lily Cuku () and Zhilbert Tafa ()

Edelweiss Applied Science and Technology, 2025, vol. 9, issue 2, 1803-1829

Abstract: Hospital readmission is a substantial burden on healthcare systems, increasing both costs and patient strain. Current traditional methods for identifying patients at high risk for readmission are often based on clinicians' judgment. This issue is especially concerning for patients with chronic conditions like diabetes, where the pressure to reduce readmissions may lead to worse outcomes. Unlike traditional methods, machine learning algorithms can analyze complex datasets to identify patterns and risk factors, resulting in more precise predictions of readmission risk. They can also facilitate better resource allocation and personalized patient care. Previous studies have applied various algorithms to predict readmissions in healthcare institutions. In this study, we apply and compare the optimized versions of different machine learning (ML) models to predict 30-day readmissions and identify important predictors driving these outcomes. Based on the predefined metrics, the analyses identify the Stochastic Gradient Descent Classifier (SGDC) as the best-performing model for the available dataset and the applied ML parameter optimization. Although ML models demonstrate potential for predicting readmissions, they are not yet fully reliable.

Keywords: Classification models; Diabetes readmission; Healthcare; Machine Learning; Predictive modelling; Readmission risk prediction. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://learning-gate.com/index.php/2576-8484/article/view/4929/1842 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:9:y:2025:i:2:p:1803-1829:id:4929

Access Statistics for this article

More articles in Edelweiss Applied Science and Technology from Learning Gate
Bibliographic data for series maintained by Melissa Fernandes ().