What does this research mean for the field?

The Random Forest machine learning classifier is highly effective at predicting 20-day hospital readmission for heart failure patients in Rwanda, outperforming other standard models with an AUC of 94%. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

September 18, 2023Journal of Personalized MedicineOpen Access

Comparing Machine Learning Classifiers for Predicting Hospital Readmission of Heart Failure Patients in Rwanda

View Full Paper

Ask AI

Bookmark

Why the study?

High hospital readmission rates and treatment costs for heart failure are major public health issues globally and in Rwanda, where machine learning could enable early interventions.

Which machine learning classifier best predicts 20-day hospital readmission in heart failure patients in Rwanda?

Structured PICO

Which machine learning classifier best predicts 20-day hospital readmission in heart failure patients in Rwanda?

Population

4,085 heart failure patients hospitalized across seven hospitals in Rwanda between January 1, 2008, and December 31, 2019.

Intervention

Machine learning classifiers (Random Forest, Support Vector Machines, K-Nearest Neighbors, Multi-Layer Perceptron, Logistic Regression, Decision Trees) to predict hospital readmission.

Comparator

Comparison among the different machine learning models.

Outcome

Hospital readmission within 20 days of hospital discharge, evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.

A Random Forest machine learning model can accurately predict 20-day hospital readmission for heart failure patients in Rwanda, potentially enabling targeted early interventions and better resource allocation.

Limitations

Data availability and quality
Cultural considerations
Particularities and complexities of the Rwandan healthcare system

Implication

Supports 20-day HF readmission risk stratification in Rwanda; leaves open prospective validation before clinical use.

Abstract

High rates of hospital readmission and the cost of treating heart failure (HF) are significant public health issues globally and in Rwanda. Using machine learning (ML) to predict which patients are at high risk for HF hospital readmission 20 days after their discharge has the potential to improve HF management by enabling early interventions and individualized treatment approaches. In this paper, we compared six different ML models for this task, including multi-layer perceptron (MLP), K-nearest neighbors (KNN), logistic regression (LR), decision trees (DT), random forests (RF), and support vector machines (SVM) with both linear and radial basis kernels. The outputs of the classifiers are compared using performance metrics including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. We found that RF outperforms all the remaining models with an AUC of 94% while SVM, MLP, and KNN all yield 88% AUC. In contrast, DT performs poorly, with an AUC value of 57%. Hence, hospitals in Rwanda can benefit from using the RF classifier to determine which HF patients are at high risk of hospital readmission.