Researchers have found a new way to detect self-harm history
By Hamilton Kahn
Click here for updates on this story
ALBUQUERQUE, New Mexico (KOAT) — A new study analyzing the health records of 1.3 million patients of the Veterans Health Administration is developing ways to fill gaps in the ability of health providers to detect a history of self-harm, according to an article on the University of New Mexico Health Sciences website.
History of self-harm is the best predictor of future self-harm and suicide risk, but clinicians’ dependence on diagnosis codes come up short on finding this important information in years of medical records, according to Christophe Lambert, corresponding author of the study and interim chief of the Division of Translational Informatics in the UNM School of Medicine’s Department of Internal Medicine.
“Better measurement can help health systems plan better, help researchers study care more accurately, and eventually help clinicians know when a patient may need a closer look,” Lambert said.
The new method being developed is called Positive Unlabeled Learning Selected Not At Random, or PULSNAR, which “learns” from patients that have a diagnostic code, then estimates how many similar patients might be among those who doesn’t have one.
“Our method can help flag both patterns for review,” said Praveen Kumar, the study’s first author. “The study could verify the first pattern, because evidence was already in the notes. The second pattern might be just as important, but confirming it would require talking with patients or using information beyond the medical record.”
The research team has also published a related study using this approach to detect under-coded opioid use disorder. It will also be apply the method to detect PTSD, depression, bipolar disorder, and sleep disorders, which otherwise may not be recognized because they aren’t in the patient’s medical record.
Please note: This story was provided to CNN Wire by an affiliate and does not contain original CNN reporting. This content carries a strict local market embargo. If you share the same market as the contributor of this article, you may not use it on any platform.