MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122158 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'ai-based medicine recommendation system using biobert and sentiment analysis.'
Inventor(s) include Dr. Suganthini. C; Ms. Ch Sree Lasya Reddy; Mr. Boyapati Manjesh; and Mr. Dhinesh Kandra.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method (100) for AI-based medicine recommendation. The method (100) receives (102) user symptom input, processes (104, 106) symptom descriptions using a BioBERT model to predict disease, analyzes (108, 110) drug reviews using sentiment analysis to rank drugs based on positive feedback, checks (114) for drug interactions between top-ranked candidates and user medications using a drug interaction database, and generates (120) medication recommendations based on predicted disease, drug ranking, and interaction verification. The BioBERT model tokenizes symptom descriptions with padding and truncation. The sentiment analysis applies VADER to generate sentiment scores, filters positive reviews, and calculates weighted ratings using review usefulness counts. Drug interaction checking queries the database, displays interacting drugs when detected, and prompts users to confirm current medications."
Disclaimer: Curated by HT Syndication.
