Population stratification for prediction of mortality in post-AKI patients

TL;DR

This paper explores using population stratification and machine learning to improve mortality prediction in post-AKI patients, aiming to enhance follow-up planning and reduce healthcare costs.

Contribution

It introduces a stratified predictive modeling approach tailored to different patient categories to improve mortality prediction accuracy after AKI.

Findings

Stratified models outperform non-stratified ones in predicting mortality.

Population-specific models increase prediction accuracy.

The approach supports personalized follow-up planning.

Abstract

Acute kidney injury (AKI) is a serious clinical condition that affects up to 20% of hospitalised patients. AKI is associated with short term unplanned hospital readmission and post-discharge mortality risk. Patient risk and healthcare expenditures can be minimised by followup planning grounded on predictive models and machine learning. Since AKI is multi-factorial, predictive models specialised in different categories of patients can increase accuracy of predictions. In the present article we present some results following this approach.