Enhancing end-stage renal disease outcome prediction: a multisourced data-driven approach

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Analysis reveals machine learning improves chronic kidney disease outcomes in 10,326 patients, suggesting better tracking.

Integrated data models achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.93, indicating superior prediction.
The use of machine learning and deep learning models allowed for effective feature engineering and enhanced prediction accuracy.
Explaining predictions through SHAP analysis helps identify key predictors and reduce bias, particularly among African American patients.
This framework supports improved clinical decisions and targeted interventions to mitigate health-care disparities in CKD management.

Li et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Analysis reveals machine learning improves chronic kidney disease outcomes in 10,326 patients, suggesting better tracking.

Integrated data models achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.93, indicating superior prediction.
The use of machine learning and deep learning models allowed for effective feature engineering and enhanced prediction accuracy.
Explaining predictions through SHAP analysis helps identify key predictors and reduce bias, particularly among African American patients.
This framework supports improved clinical decisions and targeted interventions to mitigate health-care disparities in CKD management.

Li et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark