An AI-based mental health guardrail and dataset for identifying psychiatric crises in text-based conversations.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41933065.
- Also identified by DOI 10.1038/s41746-026-02579-5.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Large language models often mishandle psychiatric emergencies, offering harmful or inappropriate advice. This study evaluated the Verily Mental Health Guardrail (VMHG) on two clinician-labeled datasets: the Verily Mental Health Crisis Dataset v1.0, containing 1800 simulated messages and the NVIDIA Aegis AI Content Safety Dataset subsetted to 794 mental health-related messages. Performance was benchmarked against OpenAI Omni Moderation Latest and NVIDIA NeMo Guardrails. The VMHG demonstrated high sensitivity (0.990) and specificity (0.992) on the Verily dataset, with an F1-score of 0.939 and high category-level sensitivity (0.917-0.992) and specificity (≥0.978). On the NVIDIA dataset, it maintained strong sensitivity (0.982) and accuracy (0.921) with reduced specificity (0.859). Compared with NVIDIA and OpenAI guardrails, the VMHG achieved significantly higher sensitivity (all p < 0.001) and comparable specificity (NVIDIA p < 0.001, OpenAI p = 0.094). Overall, the VMHG demonstrated robust, generalizable, and clinically oriented safety performance that prioritizes sensitivity to minimize missed mental health crises.