A new model was recently introduced that uses electronic health records and machine learning to predict a person’s suicidal behavior for up to two years in advance.
“Computers cannot replace care teams in identifying mental health issues,” explains Ben Reis, co-senior author on the paper from Boston Children’s Hospital. “But we feel that computers, if well designed, could identify high-risk patients who may currently be falling through the cracks, unnoticed by the health system.”
With the rise of big data, more and more researchers are leveraging AI and machine learning to identify the risks of mental health illnesses. The team used a pre-existing model on sets of data from five different health care centers, with a total exceeding 3.7 million patients.
The algorithm successfully predicted 38 per cent of the suicide attempts two years before they occurred, in a test that contained almost 40,000 attempts.
The next steps are moving towards refining the model and adding in more health data to reach the goal of helping doctors better identify patients with suicidal tendencies. “We envision a system that could tell the doctor, ‘of all your patients, these three fall into a high-risk category. Take a few extra minutes to speak with them.’”