The collaborative initiative, titled HEADS (Human‑in‑the‑loop Evaluation of Assisted Depression Screening), will run for 24 months and is designed to record and analyse roughly 4,500 clinical interviews conducted at NIMHANS and LGBRIMH.
Dr. Lekhansh Shukla, assistant professor of psychiatry at NIMHANS and principal investigator of the project, said India faces one of the world’s largest depression treatment gaps, with only about one in five sufferers receiving timely care. He added that most existing mental‑health AI tools are built on English‑language, urban datasets and therefore perform poorly in India’s diverse, non‑English clinical settings.
HEADS seeks to reverse that trend by developing artificial‑intelligence models that understand clinical conversations in the five target languages from day one. "In our earlier research, we found that even frontier models cannot understand or translate Indian languages, especially when discussion was about feelings and emotions," Dr. Shukla told The Hindu.
A core principle of the study is a strict ‘human‑in‑the‑loop’ framework, ensuring AI serves only as a decision‑aid and never replaces professional judgement. The project also incorporates a 15‑member panel of lived‑experience experts—people who have survived depression, anxiety or substance‑use disorders—who will shape study design, consent protocols, language‑evaluation groups and algorithmic bias audits.
IIT Kharagpur will lead the engineering, system development and AI‑safety work, aiming to deliver responsible, bias‑mitigated tools for clinicians. The hybrid launch event, attended by senior leadership and investigators from all partner institutions, marks what the organisers describe as a landmark step toward equitable digital mental‑health care in India.