Quantifying disparities in intimate partner violence: a machine learning method to correct for underreporting

TL;DR

This paper introduces a machine learning method to accurately estimate the relative prevalence of underreported medical conditions across groups, addressing reporting biases to inform equitable health policies.

Contribution

It extends positive unlabeled learning to estimate relative prevalence under covariate shift, even when absolute prevalence cannot be recovered, and demonstrates robustness and practical applications.

Findings

Method outperforms baselines in synthetic and real data

Accurately estimates relative prevalence despite underreporting

Shows robustness to violations of covariate shift assumption

Abstract

Estimating the prevalence of a medical condition, or the proportion of the population in which it occurs, is a fundamental problem in healthcare and public health. Accurate estimates of the relative prevalence across groups -- capturing, for example, that a condition affects women more frequently than men -- facilitate effective and equitable health policy which prioritizes groups who are disproportionately affected by a condition. However, it is difficult to estimate relative prevalence when a medical condition is underreported. In this work, we provide a method for accurately estimating the relative prevalence of underreported medical conditions, building upon the positive unlabeled learning framework. We show that under the commonly made covariate shift assumption -- i.e., that the probability of having a disease conditional on symptoms remains constant across groups -- we can recover the relative prevalence, even without restrictive assumptions commonly made in positive unlabeled learning and even if it is impossible to recover the absolute prevalence. We conduct experiments on synthetic and real health data which demonstrate our method's ability to recover the relative prevalence more accurately than do baselines, and demonstrate the method's robustness to plausible violations of the covariate shift assumption. We conclude by illustrating the applicability of our method to case studies of intimate partner violence and hate speech.