MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107618 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Ramapuram Campus on September 08, 2026, for Deep Learning For Automated Ecg Classification: Mobilenetv2-Based Transfer Learning With Clinical Application Analysis.
Inventors include Sujay S; Karthick S; and Nirmala V.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The present invention relates to a system and method for automated image analysis of electrocardiogram (ECG) images for the diagnosis of cardiac diseases and clinical decision support, by applying artificial intelligence. The validation, pre-processing, and conversion of uploaded ECG images into tensor representations are done before analysis with a transfer learning model based on the MobileNetV2. The multi-class classification module classifies Acute Myocardial Infarction, Chronic Myocardial Infarction, Arrhythmia and Normal ECG. Diagnostic models provide confidence and severity scores, probability distribution, and models of disease severity. Recommendations are given by a clinical interpretation engine and structured diagnostic reports use a module that is automated, including the diagnosis, the level of confidence, the level of severity, observations and recommended actions. The invention provides an efficient real-time ECG analysis system and facilitates deployment in hospitals, telemedicine systems, and portable healthcare systems. Total Number of Words in Abstract:138
Disclaimer: Curated by HT Syndication.
