Research published on today reports that doctors could forecast a patient’s risk of receiving a domestic abuse diagnosis years in advance by using electronic medical records as an early warning system.

Dr Ben Reis from the Children’s Hospital Boston Informatics Program and Harvard Medical School is the lead author. Researchers investigated whether the amount of historical electronic data could be used to identify high risk patients.

Reis explains: “Doctors typically do not have the time to thoroughly review a patient’s historical records during the brief clinical encounter. As a result, certain conditions that could otherwise be detected are often missed. One such condition is domestic abuse, which may go unrecognised for years as it is masked by acute complaints that form the basis of clinical encounters.”

In the United States, domestic abuse is the most frequent cause of nonfatal injury to women. Every year it accounts for more than half the murders of women. It affects both men and women and can result in serious injury and death. As a result, the authors state: “it is critical that at-risk patients be identified as early as possible.”

There is proof that screening is a valuable tool in detecting domestic abuse. But the authors judge that doctors “may not be taking full advantage of the growing amounts of longitudinal data stored in electronic health information systems.”

An analysis was completed using medical records from over 500,000 non-identifiable patients over 18 years of age. For these individuals, there was at least four years of data on admissions to hospital and visits to emergency departments. There were over 16 million diagnoses, from which some were identified as cases of abuse according to established record-keeping codes.

A scoring system was developed by the researchers. It predicted which patients were likely to receive a domestic abuse diagnosis. The system was effective in predicting future diagnoses of abuse an average of 10 to 30 months in advance.

Particular risk factors were strongly linked with a future diagnosis of abuse. The risk was highest after being seen in hospital or the emergency department for these events:
For women:
• injuries
• alcoholism
• poisoning
For men:
• mental health conditions such as depression and psychosis

In addition, researchers developed a prototype risk-visualization environment. It provides clinicians with instant overviews of longitudinal medical histories and related risk profiles at the point of care. The authors explain: “In conjunction with alerts for high-risk patients, this could enable clinicians to rapidly review and act on all available historical information by identifying important risk factors and long-term trends.”

Reis claims that these risk profiles could help doctors diagnose domestic abuse much earlier, perhaps many years in advance. He underlines that: “With increasing amounts of data becoming available, this work has the potential to bring closer the vision of predictive medicine, where vast quantities of information are used to predict individuals’ future medical risks in order to improve medical care and diagnosis.”

“Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study”
Ben Y Reis, assistant professor, Isaac S Kohane, professor, Kenneth D Mandl, associate professor
BMJ 2009; 339:b3677

Written by Stephanie Brunner (B.A.)