Researchmultimodalclinical decision supportelectronic medical recordsdomestic violence
AI Identifies Patients At Risk of IPV
9.8
Scientists published in Nature on 15 March 2026 that US researchers developed an AI tool trained on hospital records to identify patients at risk of intimate partner violence years earlier. Using records from nearly 850 IPV victims and more than 5,200 controls, a combined model reached 88% accuracy and flagged risk over three years before intervention programme entry, with planned EMR integration.
Key Points
- 1Trained models analysed structured data and clinical notes from ~850 IPV cases and 5,200 controls
- 2Combined model achieved 88% accuracy and flagged potential abuse over three years before interventions
- 3Suggests clinicians can receive early signals via EMR integration to enable proactive support
Scoring Rationale
High clinical novelty and Nature peer review, tempered by limited current deployment and need for external validation.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
250 free problems · No credit card
See all Health & Insurance problems