New Delhi: Artificial intelligence may soon help doctors “read” the brain before disease becomes visible. An Indian team has unveiled MANAS 1, a Brain Language Foundation Model built on 60,000 hours of brainwave recordings from more than 25,000 patients, with the aim of enabling earlier detection of neurological and psychiatric disorders.
Developed by Intellihealth (NeuroDx), led by neurologist Dr Puneet Agarwal, former Professor at All India Institutes of Medical Sciences, and his team, the model was launched during an AI summit and released as open source on Hugging Face. The project received computational backing under the Indian AI Mission of the Ministry of Electronics and Information Technology.
Unlike conventional AI systems, MANAS 1 is trained to interpret EEG signals — the electrical activity generated by the brain. Built with 400 million parameters, it is described by its developers as a foundational platform on which disease-specific AI tools can be developed.
Dr Agarwal told TOI that MANAS 1 is designed to “understand the basic language of the brain.” He described it as a foundation model — similar in concept to ChatGPT — that learns from large-scale EEG data to interpret brain signals that traditional tests like MRI cannot fully decode. According to him, the model creates a platform on which AI tools for epilepsy, dementia and other disorders can later be built, while also helping researchers explore aspects of brain function that remain poorly understood.
The public health argument is early access. India faces a shortage of neurologists and psychiatrists, particularly outside major cities. Brain disorders are often detected late, increasing disability and long-term costs. The developers say tools built on MANAS 1 could assist doctors at Ayushman Arogya Mandirs, community health centres and district hospitals in preliminary screening and timely referral. Any disease-specific AI model derived from the platform would require regulatory approvals before clinical deployment.
If validated at scale, such systems could help reduce the gap between symptom onset and diagnosis — a critical factor in conditions such as epilepsy and dementia.
A next-generation version, MANAS 2, is expected in the coming weeks.
As artificial intelligence advances into neuroscience, MANAS 1 signals an attempt to move from analysing language on screens to interpreting the electrical language of the brain — with implications for research, diagnosis and access to care.
