MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202631060579 A) filed by Dr. Sudhir Chandra Sur Institute Of Technology & Sports Complex, Kolkata, West Bengal, on May 13, for 'adaptive federated digital twin learning system with causal feedback optimization for early disease prediction and preventive healthcare.'
Inventor(s) include Chandrima Sinha Roy; Debashis Das; and Bhaskar Chakrabarti.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The invention provides an adaptive federated digital twin learning system for early disease prediction and preventive healthcare. The system comprises a decentralized federated learning module, a personalized digital twin simulation engine, and a causal inference engine that employs do-operator modeling to generate counterfactual outcomes. A causal feedback computation module calculates a feedback score based on the deviation between simulated counterfactuals and predicted results. An adaptive aggregation controller then utilizes a non-linear exponential function to update global model parameters, assigning higher weights to local models that exhibit greater consistency with simulated intervention outcomes. This closed-loop framework ensures high predictive accuracy, personalization, and data privacy, effectively managing the challenges of data heterogeneity in multi-modal healthcare environments."
Disclaimer: Curated by HT Syndication.
