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.
Answers are grounded in this paper and cite their sources.
An explainable machine learning framework using Extra Trees can accurately classify hypoxemia levels from PPG signals, achieving 99.09% accuracy.
This paper presents an explainable framework for peripheral oxygen saturation (SpO2) and the classification of hypoxemia levels using photoplethysmography (PPG) signals obtained from a MAX30102-based optical sensing dataset. The study utilizes the publicly available Hemoglobin PPG dataset, which includes only red and infrared channels and was initially created for hemoglobin estimation. Since there were no SpO2 annotations in that dataset, the red-infrared intensity ratios and standard oxygen saturation thresholds were modeled physiologically to provide synthetic labels. To create interpretable input features, the preprocessed signals were subjected to windowed segmentation, wavelet-based denoising, and AC/DC feature extraction. Several machine learning (ML) models were used for classification, including feedforward neural networks (FFNN), hybrid ensembles, Extreme Gradient Boosting (XGBoost), Extra Trees, and a stacking ensemble. Among these, Extra Trees achieved the best accuracy, at 99.09%. The need for interpretable, computationally effective deployment on edge devices and the small dataset size made traditional machine learning methods more appealing than deep learning. The physiological validity of important spectrum features was validated by Explainable Artificial Intelligence (XAI) modules using partial dependency analysis and permutation importance.
No takes yet. Share an insight, caveat, or question.
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 10 related papers. Consider them for comparative context: