MUMBAI, India, Nov. 21 -- Intellectual Property India has published a patent application (202531078051 A) filed by Abhilash Borah; and Dr Kshirod Sarmah, Jakhalabandha, Assam, on Aug. 17, for 'real-time heart attack detection via voice analysis using deep learning.'
Inventor(s) include Dr Kshirod Sarmah; Dr Rashmi Sarkar; Dr Sisir Kumar Rajbongshi; Dr Swapnanil Gogoi; Dr Hem Chandra Das; Dr Rajdeep Ghosh; and Dr Dharmeswar Tarang.
The application for the patent was published on Nov. 21, under issue no. 47/2025.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system and method for real-time heart attack detection using voice recordings processed via a deep learning (DL) model. By analyzing short segments of speech and identifying minute cardiac-related vocal biomarkers, the system provides a non-invasive, accessible, and rapid diagnostic tool. The solution integrates smartphone-based audio capture, preprocessing of voice samples, and prediction through a trained convolutional neural network (CNN) and Long Short-Term Memory (LSTM). This model yields high accuracy in detecting myocardial infarction (MI) events by interpreting phonetic stress patterns and laryngeal muscular tension."
Disclaimer: Curated by HT Syndication.
