Healthcare AI Safety Gap · Don't break patients
    Peer-reviewed / official13 Nov 2026·US

    AI can't yet stand in for a clinician's psychological risk assessment, crisis-line study finds

    PLOS Digital Health: comparing AI and language-analysis methods on thousands of crisis-counselling conversations and social-media posts, researchers concluded that AI tools cannot yet provide valid psychological assessments and called for stronger standards.

    ~50
    factors tested for predicting emergency intervention in crisis-counselling conversations

    What the research found

    In two studies, researchers from the Child Mind Institute, Harvard and MIT compared AI and natural-language methods for assessing psychological states on crisis-counselling conversations and public social-media posts, then used crisis conversations to model about 50 factors that predict later emergency-service intervention. Mentions of lethal means and substance use or overdose were among the strongest predictors. The authors conclude the tools cannot yet provide valid psychological assessments and set out standards for testing them.

    Why it matters for providers

    Tools that score crisis or suicide risk from text are already on the market, and this says the evidence for trusting them without a clinician isn't there yet.

    Original source
    PLOS Digital Health (Child Mind Institute, Harvard University, MIT)
    Read the full report ↗
    Peer-reviewed or official source, the most reliable tier.