Intellectual Property India Publishes Patent Application for A Computer-Implemented Dual-Model Early Risk Detection System For Gestational Diabetes Mellitus And Preeclampsia In Pregnant Women With Polyendocrine Metabolic Ovarian Syndrome Using Routine Antenatal Clinical Data.

MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641063768 A) filed by Anuhya Korrapati; and Divya Pradeep on May 20, 2026, for A Computer-Implemented Dual-Model Early Risk Detection System For Gestational Diabetes Mellitus And Preeclampsia In Pregnant Women With Polyendocrine Metabolic Ovarian Syndrome Using Routine Antenatal Clinical Data..

Inventors include Anuhya Korrapati; and Divya Pradeep.

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

Abstract: The present invention relates to a computer-implemented system and method for early risk detection of gestational diabetes mellitus (GDM) and preeclampsia in pregnant women diagnosed with Polyendocrine Metabolic Ovarian Syndrome (PMOS). The system comprises a data input module, a data validation and preprocessing module, a feature derivation module, a dual predictive modelling engine, a risk identification module, a safety override alert module, and a clinical decision aid module configured within an integrated architecture. The feature derivation module generates engineered and composite features, including metabolic and vascular risk indicators, from routinely obtainable antenatal data including PMOS-specific clinical parameters, and further derives longitudinal trend indicators across successive visits. The dual predictive modelling engine comprises two supervised machine learning models configured to generate probability-based risk scores for GDM and preeclampsia, respectively. A risk identification module compares the probability scores with predefined or calibrated thresholds to generate clinical risk flags and a dual-risk interaction profile. A safety override module generates high-priority alerts based on critical clinical parameters independent of model outputs. The system provides structured, real-time clinical decision outputs, enabling early detection, improved risk stratification, and scalable deployment across healthcare settings without reliance on specialised biomarkers. Fig. 1

Disclaimer: Curated by HT Syndication.