Intellectual Property India Publishes Patent Application for Machine Learning-Based Intelligent Drug Recommendation System For Personalized Cancer Therapy

MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641107067 A) filed by Krishna Kumar Dhakchinamoorthi; Vijaya Bhaskara Reddy. M; K. Ishwarya Devi; Dr. R. Gayathiri; Suja Alphonse A; Dr. L. Mohana Kannan; Dr. Manmohan Singhal; Kungumaraj K; Dr. Manikandan S; Narmadha Mangalagiri; L. Jhansi; and Sudha K on September 05, 2026, for Machine Learning-Based Intelligent Drug Recommendation System For Personalized Cancer Therapy.

Inventors include Krishna Kumar Dhakchinamoorthi; Vijaya Bhaskara Reddy. M; K. Ishwarya Devi; Dr. R. Gayathiri; Suja Alphonse A; Dr. L. Mohana Kannan; Dr. Manmohan Singhal; Kungumaraj K; Dr. Manikandan S; Narmadha Mangalagiri; L. Jhansi; and Sudha K.

The application for the patent was published on October 02, 2026, under issue no. 40/2026.

Abstract: Machine Learning-Based Intelligent Drug Recommendation System for Personalized Cancer Therapy is the proposed invention. The proposed invention acquires authorized genomic, transcriptomic, histopathological, radiological, clinical, laboratory, medication, and longitudinal treatment data and processes the data through modality-specific encoders to generate a unified patient representation. A multimodal oncology foundation model analyzes the representation to characterize tumor biology, disease progression, treatment history, and patient-specific therapeutic factors. An agentic AI layer evaluates candidate drugs and combinations based on molecular characteristics, therapeutic targets, predicted treatment response, toxicity risk, resistance probability, and patient biomarkers. A therapy optimization engine aggregates these outputs and generates ranked treatment recommendations with confidence scores and interpretable factors. The recommendations are presented to clinicians for expert review and approval. Subsequent treatment outcomes are incorporated into the longitudinal patient representation, enabling continuous model updating and refinement of future recommendations, thereby supporting adaptive, explainable, and personalized cancer therapy selection.

Disclaimer: Curated by HT Syndication.