New Delhi: Artificial intelligence may soon help doctors “read” the brain before diseases manifest themselves. An Indian team has launched MANAS 1, a language-based model of the brain based on 60,000 hours of brainwave recordings from more than 25,000 patients, aiming to detect neurological and psychiatric diseases earlier.The model, developed by Intellihealth (NeuroDx) and its team led by neuroscientist Dr. Puneet Agarwal, a former professor at the All India Institute of Medical Sciences, was launched during the Artificial Intelligence Summit and released as open source on Hugging Face. The project received computational support from the Indian Artificial Intelligence Mission of the Ministry of Electronics and Information Technology.Unlike traditional artificial intelligence systems, MANAS 1 is trained to interpret electroencephalogram signals – the electrical activity generated by the brain. It is built with 400 million parameters and is described by developers as a foundational platform on which disease-specific AI tools can be developed.Dr Agarwal told TOI that MANAS 1 aims to “understand the basic language of the brain”. He describes it as a basic 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 artificial intelligence tools can later be built to treat epilepsy, dementia and other diseases, while also helping researchers explore aspects of brain function that are still poorly understood.The public health argument is early access. India faces a shortage of neurologists and psychiatrists, especially outside major cities. Brain diseases are often detected late, increasing disability and long-term costs. Developers say the tool built on MANAS 1 can help doctors at Ayushman Arogya Mandirs, community health centers and district hospitals with initial screening and timely referrals. Any disease-specific AI models derived from the platform will need regulatory approval before clinical deployment.If validated at scale, such systems could help close the gap between symptom onset and diagnosis—a key factor in diseases such as epilepsy and dementia.The next generation version, MANAS 2, is expected to be launched in the coming weeks.As artificial intelligence moves toward neuroscience, MANAS 1 marks an attempt to move away from analyzing language on a screen and toward interpreting the electrical language of the brain—with implications for research, diagnosis, and access to care.
