MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202521055872 A) filed by Pragati A. Patil; Suresh Singh Rajpurohit; Dr. Thaksen Parvat; Dr. Tatwadarshi Nagarhalli; Dr. Ashwini Save; Sunita Naik; Ms. Rimsy Dua; Rina Kothari; Manthan Joshi; and Bharati Gondhalekar, Thane, Maharashtra, on June 10, for 'a blockchain based system for federated learning in the healthcare domain, and a method for the same.'
Inventor(s) include Pragati A. Patil; Suresh Singh Rajpurohit; and Dr. Thaksen Parvat.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a blockchain based system for federated learning in the healthcare domain, and a method for the same. The proposed system mainly comprises a plurality of local devices configured to perform local model training based on local dataset, and transmit the local, a communication module configured to facilitate the transmission of encrypted local model updates, a federated or central server configured to receive the local model updates, and aggregate them to develop a global model update, wherein the global model update is further transmitted to said devices for further training and predictions. The invention enables collaborative training of machine learning models across multiple organizations without sharing raw data, thereby preserving privacy, reducing communication overhead, and ensuring compliance with data protection regulations while maintaining high model accuracy."
Disclaimer: Curated by HT Syndication.
