Mass General radiologists developed a machine learning tool to identify patients at risk of intimate partner violence using imaging and clinical records.
Key Details
- 1Mass General Brigham experts created an AI program to detect domestic abuse risk.
- 2Inputs included radiology reports, imaging data, and diagnosis information.
- 3Models trained on records from 673 women experiencing domestic violence and 4,169 controls.
- 4Three AI models tested: using structured EHR data, unstructured reports, and a fusion model.
- 5Patterns in imaging—such as frequent visits and certain injury locations—inform risk prediction.
Why It Matters
Early identification of domestic violence victims remains challenging. Integrating AI decision support into radiology leverages imaging data for proactive and potentially life-saving intervention, highlighting radiology's evolving role in broader patient well-being.
Source
Radiology Business
Related News
•AuntMinnie
AI Advances in Breast Cancer Risk, CEUS Training Updates, and Imaging AI Variability
This week's top radiology news reviews AI advances in breast and lung cancer risk prediction, new CEUS training standards, and prostate screening updates with imaging modalities.
•AuntMinnie
Specialized AI Model Achieves 99% Accuracy in Cardiac MRI Interpretation
A cardiac MRI-specific AI algorithm, CMR-CLIP, demonstrated up to 99% accuracy for certain heart conditions, outperforming general AI models by up to 45.5%.
•AuntMinnie
Human-AI Collaboration Achieves 99.2% Sensitivity for PE Detection in CTPA
A large study confirms that combining radiologists with FDA-cleared AI significantly improves pulmonary embolism detection on CTPA.