A Machine Learning Model for Predicting, Diagnosing, and Mitigating Health Disparities in Hospital Readmission

TL;DR

This paper introduces a machine learning pipeline that predicts hospital readmission for diabetic patients while detecting and mitigating biases related to social determinants, leading to fairer healthcare predictions.

Contribution

The novel pipeline detects and removes biases early in data collection, improving fairness in hospital readmission predictions.

Findings

Bias mitigation improves fairness of predictions

Early bias removal enhances model accuracy and fairness

Pipeline effectively detects biases in clinical data

Abstract

The management of hyperglycemia in hospitalized patients has a significant impact on both morbidity and mortality. Therefore, it is important to predict the need for diabetic patients to be hospitalized. However, using standard machine learning approaches to make these predictions may result in health disparities caused by biases in the data related to social determinants (such as race, age, and gender). These biases must be removed early in the data collection process, before they enter the system and are reinforced by model predictions, resulting in biases in the model's decisions. In this paper, we propose a machine learning pipeline capable of making predictions as well as detecting and mitigating biases in the data and model predictions. This pipeline analyses the clinical data and determines whether biases exist in the data, if so, it removes those biases before making predictions. We evaluate the performance of the proposed method on a clinical dataset using accuracy and fairness measures. The findings of the results show that when we mitigate biases early during the data ingestion, we get fairer predictions.