September 27, 2024International Journal of Health SciencesOpen Access

Predicting hospital readmissions in diabetes patients: A comparative study of machine learning models

View Full Paper

Ask AI

Bookmark

Authors

AGAlekhya Gandra

Discussion

Member takes

Implication

Comparative analysis demonstrates that machine learning identifies high-risk diabetes readmissions, highlighting clinical factors like prior hospital stays for targeted early interventions.

Key Points

CatBoost demonstrated superior predictive performance over five other machine learning models for hospital readmission risk among patients with diabetes.
Achieving an AUC score of 0.70 alongside an accuracy of 64.2%, inpatient visit counts and hospital stay length served as the strongest predictive clinical metrics.
Comparative analysis evaluated six machine learning algorithms on the Diabetes 130-US hospitals dataset, highlighting opportunities to optimize healthcare resource planning.

Cite This Study

Alekhya Gandra (2024) studied this question.

synapsesocial.com/papers/68e57428b6db643587513dbd https://doi.org/10.53730/ijhs.v8n3.15189

View Full Paper

Ask AI

Bookmark

Implication

Comparative analysis demonstrates that machine learning identifies high-risk diabetes readmissions, highlighting clinical factors like prior hospital stays for targeted early interventions.

Predicting hospital readmissions in diabetes patients: A comparative study of machine learning models

Discussion

Member takes

Implication

Key Points

Cite This Study

Predicting hospital readmissions in diabetes patients: A comparative study of machine learning models

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider