Key result
Random Forest outperforms alternative algorithms in classifying BP from PPG signals with ~98% accuracy.
Why the study?
To explore the use of machine learning techniques to classify blood pressure based on photoplethysmography signals.
Does a Random Forest machine learning model accurately classify blood pressure categories using photoplethysmography (PPG) signals in adults?
Cross-Sectional (n=219)
Does a Random Forest machine learning model accurately classify blood pressure categories using photoplethysmography (PPG) signals in adults?
Absolute Event Rate: 97.78% vs 86.67%
A Random Forest machine learning model using PPG signals can accurately classify blood pressure categories, offering a promising non-invasive approach for continuous blood pressure monitoring.
Supports PPG-based BP classification development; hypothesis-generating and should not yet change practice.
This study explores the use of machine learning techniques to classify blood pressure (BP) based on Photoplethysmography (PPG) signals. Three popular algorithms - decision trees (DT), random forests (RF), and support vector machines (SVM) - were evaluated. The RF model outperformed the DT and SVM models with nearly 98%, 98% accuracy and F-score respectively , demonstrating its ability to capture complex non-linear relationships between PPG features and BP. It also showed robust performance in the presence of noise and variations in input PPG signals, making it a promising choice for real-world BP monitoring applications.
No takes yet. Share an insight, caveat, or question.
Dwaish et al. (2025) conducted a cross-sectional in Blood Pressure Classification (Normotension, Prehypertension, Hypertension) (n=219). Random Forest (RF) machine learning model vs. Decision Tree (DT) and Support Vector Machine (SVM) models was evaluated on Classification accuracy. The Random Forest model outperformed Decision Tree and Support Vector Machine models in classifying blood pressure from photoplethysmography signals, achieving an accuracy of 97.78%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: