MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202611100254 A) filed by Khush-Ai & Art on August 19, 2026, for A Digital Twin-Based Reinforcement Learning System For Personalized Drug Delivery To Neoplastic Lesions.
Inventor includes Atantra Das Gupta.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention relates to a digital twin-based reinforcement learning system (100) and computer-implemented method for determining patient-specific delivery parameters for an antineoplastic agent associated with a neoplastic lesion. The system (100) comprises a data acquisition arrangement (102), a digital twin generation arrangement (104), a pharmacokinetic processing arrangement (106), a lesion-state processing arrangement (108), a haematological-state processing arrangement (110), a patient-state generation arrangement (112), a reinforcement-learning processing arrangement (114), a safety processing arrangement (116), an output arrangement (118), and a feedback arrangement (120). The digital twin generation arrangement (104) generates evolving computational representation of a patient-specific physiological and pathological state. The pharmacokinetic processing arrangement (106) determines drug distribution and exposure, and reinforcement-learning processing arrangement (114) determines a dose action using a Soft Actor-Critic policy. The safety processing arrangement (116) applies pharmacological, haematological and treatment-protocol constraints to generate a safety-filtered delivery parameter, which is updated according to subsequently received patient-specific data.
Disclaimer: Curated by HT Syndication.
