MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115964 A) filed by Nitte Meenakshi Institute Of Technology, Nitte Deemed To Be University, Bengaluru; Dr Mahalakshmi; Ms. Hemashree R; and Harshitha S N on September 28, 2026, for An Intelligent Hybrid Cnn–bilstm–fuzzy Logic Framework For Ecg-Based Atrial Fibrillation Detection And Risk Stratification.
Inventors include Nitte Meenakshi Institute Of Technology, Nitte Deemed To Be University; Dr Mahalakshmi; Ms. Hemashree R; and Harshitha S N.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: ABSTRACT AN INTELLIGENT HYBRID CNN–BiLSTM–FUZZY LOGIC FRAMEWORK FOR ECG-BASED ATRIAL FIBRILLATION DETECTION AND RISK STRATIFICATION The present invention discloses a system (100) and method for electrocardiogram (ECG) based detection and risk stratification of atrial fibrillation (AF). An ECG acquisition unit (102) acquires the ECG signal, which a pre-processing module (104) denoises, normalises and segments into fixed-length heartbeat windows. A one-dimensional CNN module (106) extracts morphological features, and a BiLSTM module (108) learns forward and backward temporal dependencies between consecutive heartbeats; a classification module (110) outputs an AF probability. A fuzzy logic inference module (114) fuses this probability with RR interval, heart rate and heart rate variability through fuzzification, a Mamdani rule base and centroid defuzzification to produce an AF risk score of 0–100, which a risk stratification unit (124) maps to Normal, Moderate or High risk with a recommended clinical action. The invention provides accurate, interpretable AF risk assessment suitable for wearable, telemedicine and remote cardiac monitoring applications. Figure for publication with abstract: Fig. 1
Disclaimer: Curated by HT Syndication.
