Intimate Partner Violence and Injury Prediction From Radiology Reports

TL;DR

This study develops machine learning models to predict intimate partner violence and related injuries from radiology reports, enabling earlier intervention with high accuracy and specificity.

Contribution

The paper introduces novel predictive algorithms trained on radiology reports to identify IPV risk years before clinical intervention, advancing early detection methods.

Findings

Best model predicts IPV median 3.08 years prior to intervention

Achieves 64% sensitivity and 95% specificity

Provides error analysis for targeted clinical deployment

Abstract

Intimate partner violence (IPV) is an urgent, prevalent, and under-detected public health issue. We present machine learning models to assess patients for IPV and injury. We train the predictive algorithms on radiology reports with 1) IPV labels based on entry to a violence prevention program and 2) injury labels provided by emergency radiology fellowship-trained physicians. Our dataset includes 34,642 radiology reports and 1479 patients of IPV victims and control patients. Our best model predicts IPV a median of 3.08 years before violence prevention program entry with a sensitivity of 64% and a specificity of 95%. We conduct error analysis to determine for which patients our model has especially high or low performance and discuss next steps for a deployed clinical risk model.