Researchers in the United States have developed an AI system that identifies patients at risk of intimate partner violence years before they formally seek help or participate in intervention programs. The system was primarily trained on hospital data such as medical histories and clinical records.
By dynamically combining both system results, we achieved 88% accuracy in risk identification. This technology can detect subtle patterns in physical trauma or medical history that resemble confirmed cases of abuse, and can flag potential victims who may not disclose abuse due to fear or stigma.
Prevention timeline
Research published in naturefound that this tool can alert patients to potential abuse more than three years before they typically enter a domestic violence support program. This tool is intended to serve as a clinical decision support system rather than a diagnostic tool. This provides a signal for medical professionals to approach this subject sensitively and provide support, but it is not a substitute for a doctor’s judgment.
In this regard, Qi Duan, program director of the Division of Health Information Technology in the Division of Biomedical Imaging and Bioengineering at the National Institutes of Health, said, “This clinical decision support tool could have a significant impact on the prediction and prevention of intimate partner violence.”
Nevertheless, researchers plan to integrate AI into electronic medical record systems to provide hospitals with real-time risk assessments during routine patient care.
