Key result
RM-FIS framework outperforms conventional methods in heart disease detection with a 3314 ms fuzzification time.
Why the study?
Heart disease remains a leading cause of mortality, but conventional approaches fail to analyze cardiac severity levels capturing co-occurring conditions.
A novel deep learning and fuzzy inference framework integrating clinical and ECG data demonstrates efficient cardiac severity assessment.
May enhance multi-label ECG diagnosis; hypothesis-generating and requires prospective clinical validation before adoption.
Nowadays, Heart Disease (HD) remains one of the leading causes of mortality, representing significant global health challenges. However, conventional works have failed to analyze the cardiac severity levels, which capture the complexity of co-occurring cardiac conditions. Therefore, an intelligent clinical and Electrocardiogram (ECG) signal data-based multiple HD detection and multi-label cardiac severity analysis framework is proposed using the Risk Morph-based Fuzzy Inference System (RM-FIS). Initially, to identify early-stage HD, the Evolutionary Normalization SignReLUPlus Deep Convolutional Neural Network (EvoNorm-SRP-DCNN) is trained through clinical data collection, preprocessing, and feature extraction. Then, from the HD-detected patients, ECG signal data are collected and preprocessed, followed by adaptive waveform enhancement. Next, peak detection and relational signal integration are performed, followed by feature extraction and feature selection. Meanwhile, after peak detection, Left Ventricular Hypertrophy (LVH) signals are analyzed. Now, based on the features and LVH-analyzed scores, the multiple HDs are detected with a deep explanation. Finally, the cardiac severity level is analyzed using the RM-FIS based on the clinical risk and ECG diagnostic risk levels, providing patients’ personalized risk assessments. Thus, the proposed framework outperforms the other conventional methodologies with less Fuzzification time (3314 ms) for cardiac severity score analysis.
No takes yet. Share an insight, caveat, or question.
Veeramanikandan et al. (2026) studied Heart Disease. Risk Morph-based Fuzzy Inference System (RM-FIS) vs. Conventional methodologies was evaluated on Fuzzification time for cardiac severity score analysis. The proposed RM-FIS framework for multiple heart disease detection and cardiac severity analysis outperformed conventional methodologies with a fuzzification time of 3314 ms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: