Intellectual Property India Publishes Patent Application for Artificial Intelligence-Driven System For Patient-Specific Drug Response Prediction And Personalized Treatment Recommendation

MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641069021 A) filed by Dr. K. B. Venkata Brahma Rao; Dr. Jayaprakash H V; Mrs. K. R. Surabhi; Dayananda Sagar Academy Of Technology And Management; Mr. Kishore P. J.; Mrs. Bala Veeravatnam; Dr. Vijaya Kumar A. V.; Mrs. Anusha M.; Mrs. Rajeshwari G. L.; and Dr. Amitava Biswas on June 02, 2026, for Artificial Intelligence-Driven System For Patient-Specific Drug Response Prediction And Personalized Treatment Recommendation.

Inventors include Dr. K. B. Venkata Brahma Rao; Dr. Jayaprakash H V; Mrs. K. R. Surabhi; Mr. Kishore P. J.; Mrs. Bala Veeravatnam; Dr. Vijaya Kumar A. V.; Mrs. Anusha M.; Mrs. Rajeshwari G. L.; and Dr. Amitava Biswas.

The application for the patent was published on June 12, 2026, under issue no. 24/2026.

Abstract: The present invention relates to an artificial intelligence-driven system for patient-specific drug response prediction and personalized treatment recommendation. The system receives heterogeneous patient data including clinical records, laboratory values, prescription history, genomic markers, pharmacogenomic indicators, biomarker data, allergy records, co-morbidities, wearable data, and prior treatment outcomes. A normalization module converts the data into a standardized format, and a therapeutic feature profile generator creates a patient-specific therapeutic profile. A hybrid drug response prediction engine estimates efficacy, non-response, toxicity, adverse reaction likelihood, dose sensitivity, and confidence for candidate drugs. A safety validation engine verifies contraindications, drug interactions, organ function limitations, and patient-specific risk factors. An explainability engine identifies the clinical and molecular factors influencing each recommendation. A recommendation ranking engine generates a personalized ranked treatment output, while a privacy-preserving learning framework enables model improvement across clinical sites without centralizing complete raw patient records. Accompanied Drawing [FIGS. 1-2]

Disclaimer: Curated by HT Syndication.