MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521109938 A) filed by Indian Institute Of Technology Bombay, Maharashtra, on Nov. 12, 2025, for 'systems and methods for non-glycemic diabetes risk stratification using machine learning.'
Inventor(s) include Ashutosh Kumar; and Sneha Singh.
The application for the patent was published on Dec. 12, under issue no. 50/2025.
According to the abstract released by the Intellectual Property India: "A computer-implemented method for classifying the glycaemic status of a subject, the method comprising: receiving at a processing module, a set of input clinical data for the subject wherein said input clinical data expressly excludes direct glycaemic markers; electronically generated by said processing module, an augmented set of features is obtained by applying a feature engineering function to the input clinical data to create a plurality of derived features; applying by said processing module, a multi-stage feature selection process to the augmented set of features to identify a final optimized subset of predictive features; training a machine learning classifier using a training dataset that has been processed through said feature engineering and said multi-stage feature selection process; and generating by said processing module, an output comprising a classification of the subject's glycaemic status by inputting the subject's final optimized subset of predictive features into the trained machine learning classifier."
Disclaimer: Curated by HT Syndication.
