Intimate Partner Violence and Injury Prediction From Radiology Reports
This addresses the under-detection of IPV, a public health issue, by providing a tool for early clinical risk assessment, though it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of predicting intimate partner violence (IPV) and injury from radiology reports, achieving a model that predicts IPV a median of 3.08 years before program entry with 64% sensitivity and 95% specificity.
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.