MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521118212 A) filed by Dr. Sunil Kardani; Dr. Ghanshyam Parmar; Dr. Ashish Shah; Dr. Aarti Zanwar; Dr. Rahul Trivedi; Dr. Dillip Kumar Dash; Dr. Shivkant Patel; Dr. Kinjal Patel; Ms. Krupa Joshi; and Dr. Tejas R. Chokshi, Vadodara, Gujarat, on Nov. 27, 2025, for 'machine learning model for predicting excipient interaction in novel drug delivery systems (ndds).'
Inventor(s) include Dr. Sunil Kardani; Dr. Ghanshyam Parmar; Dr. Ashish Shah; Dr. Aarti Zanwar; Dr. Rahul Trivedi; Dr. Dillip Kumar Dash; Dr. Shivkant Patel; Dr. Kinjal Patel; Ms. Krupa Joshi; and Dr. Tejas R. Chokshi.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The invention provides a machine learning-based system for predicting excipient interactions in Novel Drug Delivery Systems (NDDS). By integrating excipient physicochemical data, engineered molecular descriptors, and advanced algorithms such as Random Forest, Gradient Boosting, Neural Networks, and Support Vector Regression, the system forecasts compatibility, stability risks, and the impact of excipient combinations on critical formulation attributes. A Compatibility Interaction Index (CII) simplifies these predictions into an easy-to-interpret numerical score. The system also includes an optimization module that recommends suitable excipients, ideal concentrations, and processing parameters, significantly reducing experimental workload. A user-friendly interface displays prediction outputs, interaction maps, and downloadable reports, while a feedback learning mechanism continually improves model accuracy. The invention enables faster, data-driven, and more reliable design of NDDS formulations."
Disclaimer: Curated by HT Syndication.
