Identifying and mitigating bias in algorithms used to manage patients in a pandemic
This addresses bias in healthcare algorithms for pandemic management, offering a practical solution to improve fairness, though it is incremental as it applies existing calibration techniques to a new domain.
The study tackled bias in COVID-19 clinical decision support systems by analyzing logistic regression models for mortality, ventilator, and inpatient status predictions, finding that simple thresholding adjustments reduced biased trials by 57% while maintaining predictive performance and increasing sensitivity from 0.527 to 0.955.
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.