Assessing Social Determinants-Related Performance Bias of Machine Learning Models: A case of Hyperchloremia Prediction in ICU Population

TL;DR

This study evaluates how social determinants influence the performance bias of machine learning models predicting Hyperchloremia in ICU patients, highlighting disparities across demographic subgroups and emphasizing the need for bias-aware model design.

Contribution

It demonstrates the impact of social determinants on ML model performance and advocates for subgroup analysis and bias mitigation in healthcare AI models.

Findings

Adding social determinants improves overall model performance.

Significant performance disparities exist across demographic subgroups.

Most models show bias when applied to underrepresented social groups.

Abstract

Machine learning in medicine leverages the wealth of healthcare data to extract knowledge, facilitate clinical decision-making, and ultimately improve care delivery. However, ML models trained on datasets that lack demographic diversity could yield suboptimal performance when applied to the underrepresented populations (e.g. ethnic minorities, lower social-economic status), thus perpetuating health disparity. In this study, we evaluated four classifiers built to predict Hyperchloremia - a condition that often results from aggressive fluids administration in the ICU population - and compared their performance in racial, gender, and insurance subgroups. We observed that adding social determinants features in addition to the lab-based ones improved model performance on all patients. The subgroup testing yielded significantly different AUC scores in 40 out of the 44 model-subgroup, suggesting disparities when applying ML models to social determinants subgroups. We urge future researchers to design models that proactively adjust for potential biases and include subgroup reporting in their studies.