Intellectual Property India Publishes Patent Application for 'An Automated Machine-Learning System For Fetal Health Prediction Using Cardiotocography (CTG) Data' Filed by Vellore Institute Of Technology

MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641024383 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on March 1, for 'an automated machine-learning system for fetal health prediction using cardiotocography (ctg) data.'

Inventor(s) include Prabhu J; Prakash M; and Nandhitha H.

The application for the patent was published on March 13, under issue no. 11/2026.

According to the abstract released by the Intellectual Property India: "The present invention relates to an automated machine-learning system and method for fetal health prediction using cardiotocography (CTG) data are 5 disclosed. the system comprises a data acquisition module configured to receive structured CTG measurements including clinically validated fetal heart rate and uterine contraction features; a data preprocessing module configured to perform exploratory data analysis, normalization, and stratified dataset partitioning while preserving class distribution; and a class-imbalance handling module configured 10 to compute class or sample weights based on inverse-frequency metrics. the system further includes an explainability-driven feature selection module configured to identify clinically significant CTG features, a model learning module configured to train a plurality of machine-learning classifiers using the selected features, and an ensemble stacking module configured to combine 15 outputs of the trained classifiers to generate a final prediction. an explainable artificial intelligence module is provided to generate global and local explanations for prediction decisions, and a prediction and interface module outputs a fetal health classification selected from Normal, Suspect, and Pathological along with associated interpretability information. the disclosed method implements an end-20 to-end automated pipeline that transforms CTG measurements into accurate and interpretable fetal health assessments, thereby supporting clinically informed decision-making."

Disclaimer: Curated by HT Syndication.