In a study funded by the National Institutes of Health (NIH), researchers created new suicide risk prediction models using data in electronic health records from the Indian Health Service (IHS).
The models correctly identified people who attempted or died by suicide within 90 days of their last healthcare visit 82% of the time. This is 18% better than current screening methods, which were accurate only 64% of the time—just slightly better than chance (50%).
The findings suggest these models may be an important way to reduce suicide risk in health care settings that serve American Indian and Alaska Native populations.
|