MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641005992 A) filed by Easwari Engineering College; Srm Institute Of Science And Technology, Chennai, Tamil Nadu, on Jan. 21, for 'a machine learning based vocal screening method for respiratory conditions.'
Inventor(s) include Dr. B. Chandra; D Divya Darshini; and Harshini S J.
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: "Diseases of the respiratory system continue to be among the top causes of morbidity and mortality worldwide, with its delayed diagnoses often resulting in serious complications and advances to chronicity. The study designs and develops a deep learning framework to reconcile these limitations by 10 developing a computerized framework for the characterization and early diagnosis of pathological lung sounds. In the workflow, the recordings of lung sound signals, which are heavily preprocessed utilizing the MATLAB to reduce noise and enhance purity of the signal. More advanced feature extraction methods are then used to amplify temporal and spectral features. This 15 hybridization increases the positivity of both models, while enabling persistent classification of abnormal respiratory events, including wheezes, crackles, rhonchi, and additional pathological features. The framework could permit early intervention based on objective or consistent modes of monitoring that can provide superior results to our patients, and ideally diminish our healthcare 20 burden."
Disclaimer: Curated by HT Syndication.
