Representative image (IANS)
NEW DELHI – Artificial intelligence may soon help doctors “read” the brain before disease becomes visible. An Indian team has unveiled MANAS 1, a basic model of brain language based on 60,000 hours of brainwave recordings from more than 25,000 patients, with the aim of enabling early detection of neuropsychiatric disorders.Developed by Intellihealth (NeuroDx), led by neurologist Dr Puneet Agarwal, former professor at the All India Institutes of Medical Sciences, and his team, the model was launched during the AI Summit and released as open source on Hugging Face. The project received computational support under the Indian Artificial Intelligence Mission of the Ministry of Electronics and Information Technology.Unlike traditional AI systems, MANAS 1 is trained to interpret electroencephalogram (EEG) signals, which is the electrical activity generated by the brain.
Designed using 400 million parameters, its developers describe it as a foundational platform on which to develop disease-specific AI tools.Dr Agarwal told TOI that MANAS 1 is designed to “understand the basic language of the brain”. He described 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 decipher.
According to him, the model creates a platform on which AI tools can be built to treat epilepsy, dementia and other disorders, 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 disorders are often discovered late, leading to increased disability and long-term costs.
Developers say tools built on MANAS 1 can help doctors at Ayushman Arogya Mandirs, community health centers and district hospitals in initial screening and timely referral. Any disease-specific AI model derived from the platform will require regulatory approvals prior to clinical deployment.If widely validated, such systems could help reduce the gap between symptom onset and diagnosis, a crucial factor in conditions such as epilepsy and dementia.The next generation version, MANAS 2, is expected to be released in the coming weeks.As artificial intelligence advances in neuroscience, Manas 1 marks an attempt to move from analyzing language on screens to interpreting the electrical language of the brain, with implications for research, diagnosis, and access to care.
