Key result
RBF SVM classifier with BFPA features achieves ~98% accuracy distinguishing CHF from NSR.
Why the study?
The study aimed to explore the earlier detection of CHF and allied cardiovascular diseases such as Afib from ECG signals using nature-inspired optimization techniques.
Does the use of nature-inspired optimization techniques and specific classifiers improve the detection of congestive heart failure and atrial fibrillation from ECG signals?
Does the use of nature-inspired optimization techniques and specific classifiers improve the detection of congestive heart failure and atrial fibrillation from ECG signals?
An SVM (RBF) classifier utilizing Binary Flower Pollination Algorithm features demonstrated high accuracy in detecting congestive heart failure and atrial fibrillation from ECG signals.
Answers are grounded in this paper and cite their sources.
ECG ML classifiers need prospective validation before use; leaves open whether optimization algorithms enhance arrhythmia detection.
This paper explores the earlier detection of CHF, and its allied Cardio Vascular Diseases (CVD) like Atrial Fibrillation (Afib) from nature-inspired optimization techniques using cardiac signals. The Beth Israel Deaconess Medical Centre (BIDMC) CHF, MIT-BIH-Afib, and Normal Sinus Rhythm (NSR) databases from the Physionet repository are utilized in this research. The Flower Pollination Algorithm (FPA), Binary Flower Pollination Algorithm (BFPA), and BFPA with Greedy Crossover approaches are applied to extract the features of CHF, Afib, and NSR cardiac classes ECG signals. Then extracted features are given into appropriate classifiers such as the SVM (Linear), SVM (Polynomial), SVM (RBF), WKNN, and NBC classifiers. The classifiers’ performance is assessed and compared by the standard performance benchmarks, such as Accuracy, F1 Score, Geometric Mean, Kappa Coefficient and Error Rate. The SVM (RBF) classifier with BFPA features achieved 97.71% overall average accuracy along with a 0.9540 kappa coefficient in {CHF} vs. {NSR} cardiac abnormality detection. The SVM (RBF) classifier with BFPA features reached 89.59% overall average accuracy along with a 0.7935 kappa coefficient in {Afib} vs. {NSR} cardiac class detection. As a result, the SVM (RBF) classifier with BFPA features outclasses all other classification techniques in detecting {CHF} vs. {NSR} cardiac abnormality classes.
No takes yet. Share an insight, caveat, or question.
Shankar et al. (2022) studied Congestive Heart Failure and Atrial Fibrillation. SVM (RBF) classifier with BFPA features vs. Other classifiers (SVM Linear, SVM Polynomial, WKNN, NBC) was evaluated on Overall average accuracy in CHF vs. NSR detection. The SVM (RBF) classifier with BFPA features achieved 97.71% overall average accuracy and a 0.9540 kappa coefficient in detecting congestive heart failure versus normal sinus rhythm.
Synapse has enriched 10 related papers. Consider them for comparative context: