Crisis text tool predicts imminent suicide risk in new chats after training on 16,000 conversations
When people reach out during a mental health crisis, a top priority for counselors is identifying those at high risk of suicide. The distressed person's language holds critical clues, and a new tool developed by scientists at MIT's McGovern Institute for Brain Research is designed to pick up on and rapidly evaluate those signals.
MIT scientists have created a tool that can predict imminent suicide risk based on text conversations with crisis counselors. The tool, developed by Daniel Low and Satrajit Ghosh, uses a customized list of words and phrases linked to 49 suicide risk factors to analyze conversations and estimate an individual's risk. The tool was trained on 16,000 text conversations from the Crisis Text Line, where volunteers provide confidential text-based support to people in distress.
The researchers focused on identifying the most predictive factors for imminent risk, finding that expressions of active suicidal ideation, self-injury, and lethal means were the strongest indicators of suicide risk. The tool assigns weights to different risk factors, with mentions of lethal means being heavily weighted. The study, published in the Journal of Psychopathology and Clinical Science, suggests that the tool could help clinicians prioritize the most critical risk factors during mental health crises.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
