Key result
Extra Trees machine learning model achieves ~99% accuracy classifying hypoxemia levels from PPG signals.
Why the study?
There is a need for an interpretable, computationally effective framework deployable on edge devices to classify SpO2 and hypoxemia levels from PPG signals.
Population
Photoplethysmography signals from the publicly available Hemoglobin PPG dataset
Comparison
Machine learning models including FFNN, hybrid ensembles, XGBoost, Extra Trees, and stacking ensemble
Authors
Loading...
May enable PPG-based SpO2 monitoring; leaves open prospective clinical validation before adoption.
An explainable machine learning framework using Extra Trees can accurately classify hypoxemia levels from PPG signals, achieving 99.09% accuracy.
Meghana et al. (2026) studied Hypoxemia. Extra Trees machine learning model vs. Other machine learning models (FFNN, XGBoost, hybrid ensembles, stacking ensemble) was evaluated on Classification accuracy. An Extra Trees machine learning model achieved 99.09% accuracy in classifying hypoxemia levels using photoplethysmography signals.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: