Key result
A Support Vector Machine algorithm using PPG signals predicts vascular age with 99% accuracy.
Why the study?
Cardiovascular diseases pose a significant global health challenge, requiring effective early risk assessment, and non-invasive methods to assess arterial stiffness and predict vascular age using PPG and machine learning are needed.
Does a machine learning algorithm using PPG signals accurately predict vascular age in healthy adults?
Does a machine learning algorithm using PPG signals accurately predict vascular age in healthy adults?
A Support Vector Machine algorithm using non-invasive PPG signals can predict vascular age with 99% accuracy, offering a potential tool for early cardiovascular risk detection.
PPG-based SVM may aid noninvasive vascular age estimation; leaves open prospective validation before clinical adoption.
Cardiovascular diseases (CVDs) pose a significant global health challenge, necessitating effective strategies for early risk assessment and intervention. Arterial stiffness, a critical parameter within the cardiovascular system, is considered a primary risk factor for CVD development. This parameter undergoes natural age-related structural and functional changes in arterial walls, resulting in increased arterial stiffness and reduced elasticity. These changes contribute to vascular aging and alter pulse wave velocity. Photoplethysmography (PPG) offers a non-invasive means to assess these alterations. Our research leverages PPG in combination with machine learning to develop a portable, non-invasive method for predicting vascular age. We identify and select 21 features from the fiducial points of the digital artery PPG signals obtained from simulated pulse waves across a diverse sample of healthy adults aged 25 to 75 years, its first derivative, and its second derivative waveforms. We assess the performance of machine learning algorithms, including Decision Tree, k-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Among these algorithms, SVM outperformed the others, achieving an accuracy, precision, recall, and F1 score of 99%. This high accuracy underscores the potential of SVM in predicting vascular age. Accurate vascular age prediction within the healthy population has the potential to establish age-specific benchmarks, aiding in the detection of outliers indicative of accelerated cardiovascular aging or underlying cardiovascular diseases.
No takes yet. Share an insight, caveat, or question.
Abrisham et al. (2023) studied Healthy adults. Support Vector Machine (SVM) using PPG signals vs. Decision Tree and k-Nearest Neighbors (KNN) was evaluated on Accuracy, precision, recall, and F1 score for predicting vascular age. A Support Vector Machine algorithm using 21 features from photoplethysmography signals predicted vascular age with 99% accuracy, precision, recall, and F1 score.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: