(Press-News.org) Researchers at Mass General Brigham have developed a series of artificial intelligence (AI) tools that uses machine learning to identify individuals who may be at risk for intimate partner violence (IPV) using information from their electronic medical records (EMRs). In a study published in npj Women’s Health, the researchers report the tools could detect IPV up to four years before the individual sought care at a domestic violence treatment center. The findings highlight its potential for proactive screening and supporting healthcare providers in initiating earlier conversations about IPV with patients.
"Our research offers proof of concept that AI can support clinicians in flagging possible abuse earlier," said Bharti Khurana, MD, MBA, principal investigator, corresponding and senior author, founding director of the Trauma Imaging Research and Innovation Center and an emergency radiologist in the Mass General Brigham Department of Radiology. “Earlier identification of intimate partner violence and future risk may enable clinicians to intervene sooner and help prevent significant mental and physical health consequences.”
More than one-third of women and 1 in 10 men will experience IPV in their lifetimes; yet, despite its high prevalence, people rarely disclose IPV to health providers due to fear, stigma, or financial or psychosocial dependence on the person abusing them. Prior research shows that people experiencing IPV are more likely to disclose abuse if asked privately by a trusted health provider in a trauma-informed manner.
To promote earlier identification and intervention by health providers, Khurana’s research team, working with collaborators at Massachusetts Institute of Technology (MIT) led by Dimitris Bertsimas, PhD, trained three machine-learning models using EMR data from 673 women who visited a domestic abuse intervention and prevention center at a U.S. academic health center between 2017 and 2022, as well as 4,169 demographically matched controls who did not report IPV.
The three AI models tested included a tabular model using structured EMR data such as diagnoses, medications and social deprivation index based on zip code; a notes model using unstructured clinical notes, and radiology and emergency department reports; and a fusion model combining both data types called Holistic AI in Medicine (HAIM).
When tested on 168 patients who visited the IPV intervention and prevention center in the same timeframe and 1,043 controls, all three models displayed high accuracy, with the fusion model achieving the highest (88%). When tested with time-stamped, archived medical records, the fusion model could predict 80.5% of cases in advance—on average more than 3.7 years before patients sought care.
The models were then validated with data from two additional patient groups that weren’t included in the training or testing data, and controls, finding similarly high accuracies.
Previous research led by Khurana found that women who frequently undergo imaging studies at the emergency department and have specific types of injuries are more likely to later report IPV. This new AI research identified additional risk factors for IPV: People with mental health disorders, chronic pain, and frequent emergency department visits were more likely to experience IPV, whereas patients who regularly accessed preventive services like mammograms and immunizations had a lower risk.
The authors note the AI tools were developed and validated in patients who had sought care for or disclosed IPV, which may limit accuracy in predicting IPV in individuals who are less likely to seek care or disclose IPV to providers. In addition, the control group in the training data may have included false negatives, or patients who were experiencing IPV but did not report it, which could reduce model accuracy. Future training with larger, more diverse patient datasets over longer time periods will improve its accuracy, noted Khurana.
Authorship: In addition to Khurana and Bertsimas, co-authors at Mass General Brigham include Jiayi Gu, Kimberly Villalobos Carballo and Yu Ma.
Disclosures: The authors declare no competing interests.
Funding: This research was funded by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) and the Office of the Director, National Institutes of Health (1R01EB032384; PI: Khurana)
Paper cited: Gu et al. “Leveraging multimodal machine learning for accurate risk identification of intimate partner violence” npj Women’s Health, DOI: 10.1038/s44294-025-00126-3
###
About Mass General Brigham
Mass General Brigham is an integrated academic health care system, uniting great minds to solve the hardest problems in medicine for our communities and the world. Mass General Brigham connects a full continuum of care across a system of academic medical centers, community and specialty hospitals, a health insurance plan, physician networks, community health centers, home care, and long-term care services. Mass General Brigham is a nonprofit organization committed to patient care, research, teaching, and service to the community. In addition, Mass General Brigham is one of the nation’s leading biomedical research organizations with several Harvard Medical School teaching hospitals. For more information, please visit massgeneralbrigham.org.
END
Embargoed for Release
Friday, March 13, 2026
6 a.m. EDT
Contact:
NIH Office of Communications
A team of researchers funded by the National Institutes of Health (NIH) have developed an artificial intelligence (AI) tool that provides decision support to clinicians by predicting if patients are at risk of intimate partner violence (IPV). Using data routinely collected during medical visits, the team trained a machine-learning model, a type of AI, that was highly accurate in detecting IPV among patients ...
Roadmap shows how to achieve good lives for all and a safe climate by reorienting production and distribution toward well-being and ecological transformation instead of capital accumulation and elite consumption.
Governments’ attempts to achieve climate goals are falling short, in large part because wealthy economies are continuing to pursue economic growth. As these economies ramp up production and consumption, they make climate mitigation more difficult to achieve. As a result, the Paris Agreement is slipping out of reach, putting nature and human societies in jeopardy.
Post-growth ...
To survive in areas where it is difficult to photosynthesize, some organisms adopt unique strategies. Osaka Metropolitan University researchers have found that a freshwater alga captures far-red light as an additional energy source by arranging ordinary chlorophyll in an extraordinary way.
Far-red light lies beyond the optimal range for photosynthesis for many organisms. Yet in shaded forests and murky waters, where this light dominates, plants and algae still pull off photosynthesis, making something out of almost nothing.
“Whilst certain cyanobacteria use specialized chlorophylls to absorb far-red light, many plants and algae achieve the same effect by reorganizing ordinary ...
Ice cores taken from glaciers reveal the air pollution of the past, using atmospheric particles incorporated in snow that fell on the glacier and became ice. Now, scientists have extracted a record of thousands of years’ worth of air pollution from 9.5 meters of ice at the Weißseespitze glacier, close to the border between Austria and Italy. But this ice is under threat from global warming, and scientists warn that it is now a race against time to capture critical climate information locked in these glaciers before it’s gone forever.
“These ...
Fleeting electron-hole pairs are giving scientists a new window into optimizing light-emitting devices (LEDs). Using quantum magnetic resonance, Osaka Metropolitan University researchers have discovered how shifting internal electric fields dictate whether these devices shine brightly or dimly.
Light-emitting electrochemical cells (LECs) are simple, flexible, and low-cost thin-film devices that generate light from an electric current. Unlike conventional organic LEDs, LECs contain just a single active layer — an organic semiconductor blended with mobile ions — sandwiched between two electrodes. This structural simplicity makes them promising tools for next-generation light-emitting ...
Gastrointestinal tract diseases affect millions worldwide, and traditional drug delivery methods suffer from low targeting efficiency and potential side effects due to systemic drug distribution. Magnetic soft robots have emerged as a revolutionary solution for minimally invasive medical operations, thanks to their small size, untethered drive, and agile motion. However, existing magnetic soft robots face critical limitations in multi-angle folding, real-time reconfigurable magnetization, and adaptability to the irregular, confined gastrointestinal cavity environment, hindering their clinical application ...
MARCH 2026 TIP SHEET
Colorectal Cancer
Sylvester Expert Leads Prevention Efforts for High-Risk Colorectal Cancer Patients
March is Colorectal Cancer Awareness Month and an ideal time to focus on the third most common cancer in the U.S. Many people know the importance of early detection for effective treatment, but fewer are aware that the disease sometimes has a genetic cause. Daniel Sussman, M.D., leads a gastroenterology high-risk prevention clinic at Sylvester. “We help identify people who are at increased risk for cancer,” he explains, adding that the clinic facilitates genetic testing to see if there’s a heritable cause. Either way, the clinic then ...
Researchers at Nagoya University in Japan, in collaboration with university spinout NU-Rei Co., Ltd., are presenting six advances in the growth of gallium oxide (Ga₂O₃), a semiconductor material with strong potential for next-generation power devices used in electric vehicles, power conversion systems, and space applications. Gallium oxide is attracting growing interest in the power semiconductor industry because it can in principle produce higher voltage devices with relatively abundant, lower-cost raw materials.
The results are being presented at the spring meeting of the Japan Society of Applied Physics (March 15-18, 2026) by a research group ...
Hyperarousal plays an important role in mental disorders. It influences the severity of insomnia, depression, anxiety, post-traumatic stress disorder (PTSD), and ADHD. Yet it is striking that researchers do not always mean exactly the same thing when they use the term “hyperarousal.” Researchers at the Netherlands Institute for Neuroscience therefore investigated whether different forms of hyperarousal exist.
“Within sleep research, we already know a great deal about the role of hyperarousal in insomnia,” says first author Tom Bresser. “But hyperarousal ...
AI-powered toys that “talk” with young children should be more tightly regulated and carry new safety kitemarks, according to a report that warns they are not always developed with children’s psychological safety in mind.
The recommendation appears in the initial report from AI in the Early Years: a University of Cambridge project and the first systematic study of how Generative AI (GenAI) toys capable of human-like conversation may influence development in the critical years up ...
