MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641101630 A) filed by Vignans Nirula Institute Of Technology And Science For Women on August 22, 2026, for An Intelligent Predictive Framework For Early Diagnosis And Risk Stratification Of Diabetes Mellitus.
Inventors include Jagadish Kalava; G. Kusuma Harinadh; G. Rohini Phaneendra Kumari; Srikanth Kilaru; Konakanchi Sravanthi; Mandalapu Charanya; Govathoti Vineetha Raj; and Maheswarapu Deepika Veera Naga Rajyalakshmi.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: Utilising machine learning algorithms in conjunction with clinical data analysis, the present invention pertains to an Intelligent Predictive Framework for the Early Diagnosis and Risk Stratification of Diabetes Mellitus. By analysing patients' demographic, physiological, biochemical, medical history, and clinical data, the Intelligent Predictive Framework for Early Diagnosis and Risk Stratification of Diabetes Mellitus uses an integrated computational scheme to identify individuals with a higher risk of developing diabetes. Clinical data acquisition, adaptive data preprocessing, intelligent feature optimisation, machine learning prediction engine, diabetes risk stratification, explainable artificial intelligence, and clinical decision support are all components of the Intelligent Predictive Framework for Early Diagnosis and Risk Stratification of Diabetes Mellitus. In order to prepare the data for further processing, the preprocessing module cleans, normalises, checks for outliers, and handles missing values. In order to conduct efficient predictive analysis, the feature optimisation module identifies critical clinical features. To forecast the occurrence of diabetes, a machine learning prediction engine makes use of supervised learning methods like Support Vector Machine, Decision Tree, Random Forest, and Logistic Regression. All three scores – risk score, confidence score, and probability - of the expected case are generated by the risk stratification module. A machine learning module that can be explained is helpful in boosting interpretability by revealing the clinical factors that are significant for prediction. A clinical decision support module can be useful in making adjustments, referrals, making life changes, diagnosis, and prevention.
Disclaimer: Curated by HT Syndication.
