HEADS to bridge India’s mental healthcare gap with AI

NIMHANS in collaboration with IIT Kharagpur, and Lokopriya Gopinath Bordoloi Regional Institute of Mental Health, Tezpur, to formally launch HEADS (Human-in-the-loop Evaluation of Assisted Depression Screening) on September 24

Updated - September 24, 2026 10:20 am IST - Bengaluru

The two-year study aims to build and evaluate AI-assisted approaches for the early identification and screening of depression. | Photo Credit: File photo

To address India’s alarming mental healthcare gap, NIMHANS in collaboration with the Indian Institute of Technology (IIT) Kharagpur, and the Lokopriya Gopinath Bordoloi Regional Institute of Mental Health (LGBRIMH), Tezpur, will formally launch a collaborative project titled ‘HEADS’ (Human-in-the-loop Evaluation of Assisted Depression Screening) on Thursday.

Funded by the Wellcome Trust, a major international charity foundation, the two-year study aims to build and evaluate AI-assisted approaches for the early identification and screening of depression. The initiative places a strong emphasis on Indian regional languages, specifically Kannada, Assamese, Hindi, Bengali, and English, which have historically remained substantially underrepresented in mental health AI research.

Bridging multilingual gap

Lekhansh Shukla, assistant professor of psychiatry at NIMHANS and principal investigator of the project, said India carries one of the world’s largest depression treatment gaps, where only about one in five individuals affected by depression receives timely, appropriate care.

During the project’s hybrid launch event at NIMHANS, experts will highlight the critical limitation of existing digital health innovations. Most mental health AI tools are built using English-language, urban datasets, rendering them ineffective in diverse, non-English clinical settings, he said.

“In our earlier research, we found that even frontier models cannot understand or translate Indian languages, especially when discussion was about feelings and emotions. HEADS instead builds for Indian languages from day one, developing artificial intelligence that understands clinical conversations in Kannada, Hindi, Bengali, Assamese, and English,” Dr. Shukla told The Hindu.

A central principle of the project is a strict ‘human-in-the-loop’ framework, ensuring that AI tools serve purely as supportive clinical decision-aids to help clinicians recognise symptoms earlier without ever replacing professional clinical judgment.

In a pioneering effort for Indian mental health research, the study has embedded a 15-member panel of Lived Experience Experts - individuals who have survived depression, anxiety, or substance use disorders - across every phase of the project. This panel has actively shaped the study’s design and informed consent protocols. They will also participate in language-evaluation groups across all targeted Indian languages, audit AI algorithms for hidden bias and stigmatising language, and stress-test systems before deployment, the doctor said.

Over its 24-month duration, the HEADS project will record and analyse approximately 4,500 clinical interviews across healthcare sites at NIMHANS and LGBRIMH. Meanwhile, IIT Kharagpur will lead the core engineering, system development, and AI-safety work to ensure responsible deployment. Senior leadership, investigators, and project team members across all partner institutions attended the hybrid launch, marking a landmark step toward equitable digital mental healthcare in India.

Published - September 23, 2026 08:37 pm IST

Terms & conditions | Institutional Subscriber

Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.