Key result
PPG-based K-Nearest Neighbors machine learning achieves ~98% accuracy in classifying cardiac arrhythmias.
Why the study?
ECG-based arrhythmia detection has limitations for long-term monitoring, prompting evaluation of non-invasive photoplethysmogram (PPG) signals to classify cardiac arrhythmias.
Can machine learning models accurately classify cardiac arrhythmias using features extracted from non-invasive photoplethysmogram (PPG) signals?
Can machine learning models accurately classify cardiac arrhythmias using features extracted from non-invasive photoplethysmogram (PPG) signals?
Machine learning algorithms, particularly K-Nearest Neighbors and Ensemble techniques, can accurately classify multiple types of cardiac arrhythmias using non-invasive photoplethysmogram (PPG) signals.
High-accuracy PPG-ML arrhythmia classification is hypothesis-generating; prospective validation required before clinical adoption.
Worldwide, Cardiovascular Diseases (CVDs) are the leading cause of death. Patients at high cardiovascular risk require long-term follow-up for early CVDs detection. Cardiac arrhythmia detection through the electrocardiogram (ECG) signal has been the basis of many studies. This technique does not provide sufficient information in addition to a high false alarm potential. In addition, the electrodes used to record the ECG signal are not suitable for long-term monitoring. Recently, the photoplethysmogram (PPG) signal has attracted great interest among scientists as it provides a non-invasive, inexpensive, and convenient source of information related to cardiac activity. In this paper, the PPG signal (online database Physio Net Challenge 2015) is used to classify different cardiac arrhythmias, namely; tachycardia, bradycardia, ventricular tachycardia, and ventricular flutter/fibrillation. The PPG signals are pre-processed and analyzed for feature extraction. A total of 41 features are used for cardiac arrhythmias' classification using four machine-learning techniques; Decision Trees (DT), Support Vector Machines (SVM), K-Nearest Neighbors (KNNs), and Ensembles. The results show a high-throughput evaluation with an accuracy of 98.4% for the KNN technique with a sensitivity of 98.3%, 95%, 96.8%, and 99.7% for bradycardia, tachycardia, ventricular flutter/fibrillation, ventricular tachycardia, respectively. The outcomes of this work provide a tool to correlate the properties of the PPG signal with cardiac arrhythmias and thus the early diagnosis and treatment of CVDs.
No takes yet. Share an insight, caveat, or question.
Qananwah et al. (2023) studied Cardiac arrhythmias (n=750). Machine learning classification (K-Nearest Neighbors) using PPG signals vs. Other machine learning models (Decision Trees, Support Vector Machines, Ensembles) was evaluated on Overall classification accuracy. A K-Nearest Neighbors machine learning model using selected photoplethysmography features achieved an overall accuracy of 98.4% in classifying cardiac arrhythmias.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: