Intellectual Property India Publishes Patent Application for Machine Learning-Based Early Prediction Of Chronic Bronchitis And Copd Symptoms To Support Patient Care

MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611100492 A) filed by Madan Mohan Malaviya University Of Technology on August 19, 2026, for Machine Learning-Based Early Prediction Of Chronic Bronchitis And Copd Symptoms To Support Patient Care.

Inventors include Manjeet Kumar Jaiswar; and Dr. Shailendra Pratap Singh.

The application for the patent was published on October 23, 2026, under issue no. 43/2026.

Abstract: A machine learning-based system and method provide early prediction of chronic bronchitis and Chronic Obstructive Pulmonary Disease (COPD) symptoms using a standardized 14-feature spirometry dataset. The system ingests clinical symptoms and spirometry parameters, including pre- and post-bronchodilator values for FEV_1, FVC, and FEF. A preprocessing pipeline normalizes the features, calculates percentage-predicted values, and measures bronchodilator responsiveness. The preprocessed data is classified using machine learning algorithms—specifically Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), and Multi- Layer Perceptron (MLP)—to evaluate non-linear patterns. The models generate an automated diagnostic output identifying the presence of chronic bronchitis and categorizing symptoms into obstructive or non-obstructive pulmonary conditions, achieving high accuracy up to 90%. Deployable on CPU, GPU, or hybrid platforms, the system integrates into hospital information networks as a scalable, objective clinical decision-support tool.

Disclaimer: Curated by HT Syndication.