Identifying and mitigating bias in algorithms used to manage patients in a pandemic

TL;DR

This study shows that simple calibration methods can significantly reduce bias in COVID-19 clinical decision models without sacrificing predictive accuracy, promoting fairer healthcare outcomes.

Contribution

The paper introduces calibration techniques during training that effectively mitigate bias in COVID-19 predictive models using real-world data.

Findings

57% reduction in biased trials after calibration

Predictive performance (AUC) remained stable

Sensitivity increased from 0.527 to 0.955 after calibration

Abstract

Numerous COVID-19 clinical decision support systems have been developed. However many of these systems do not have the merit for validity due to methodological shortcomings including algorithmic bias. Methods Logistic regression models were created to predict COVID-19 mortality, ventilator status and inpatient status using a real-world dataset consisting of four hospitals in New York City and analyzed for biases against race, gender and age. Simple thresholding adjustments were applied in the training process to establish more equitable models. Results Compared to the naively trained models, the calibrated models showed a 57% decrease in the number of biased trials, while predictive performance, measured by area under the receiver/operating curve (AUC), remained unchanged. After calibration, the average sensitivity of the predictive models increased from 0.527 to 0.955. Conclusion We demonstrate that naively training and deploying machine learning models on real world data for predictive analytics of COVID-19 has a high risk of bias. Simple implemented adjustments or calibrations during model training can lead to substantial and sustained gains in fairness on subsequent deployment.