MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049888 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Ramapuram Campus, Chennai, Tamil Nadu, on April 20, for 'ecg based classification for depressive disorder using convolutional neural networks.'
Inventor(s) include Balaragavi S; Charan Nithish M; and Dr Sahunthala S.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "Visual analysis of physiological signals provides meaningful insight into mental health disorders where conventional diagnostic approaches may be slow, subjective, or inconsistent. This invention introduces a deep learning-based ECG classification system designed to identify depressive disorder levels through automated interpretation of waveform-derived image representations. The system processes ECG signals stored in MATLAB (.mat) format and converts segmented waveform windows into structured two-dimensional images, enabling efficient spatial pattern extraction using an InceptionV3 convolutional neural network. A preprocessing pipeline performs filtering, normalization, and segmentation to ensure high-quality input, while the classification module employs a softmax layer to distinguish bipolar disorder, clinical depression, and schizophrenia. Explainable AI mechanisms such as Grad-CAM highlight waveform regions contributing to predictions, improving transparency and clinical trust. Implemented using deep learning frameworks with GPU acceleration, the system supports scalable, non-invasive assessment for healthcare, telemedicine, and research applications."
Disclaimer: Curated by HT Syndication.
