Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approaches
This work addresses a gap in comprehensive comparisons for researchers and practitioners in clinical applications using PPG data, though it is incremental as it benchmarks existing methods rather than introducing new ones.
The authors tackled the problem of selecting optimal input representations and models for machine learning analysis of photoplethysmography (PPG) data by benchmarking feature, image, and signal-based approaches. They found that deep neural networks, particularly modern convolutional neural networks, achieved the best results for blood pressure and atrial fibrillation prediction, with shallow CNNs also being competitive in some tasks.
Photoplethysmography (PPG) is a widely used non-invasive physiological sensing technique, suitable for various clinical applications. Such clinical applications are increasingly supported by machine learning methods, raising the question of the most appropriate input representation and model choice. Comprehensive comparisons, in particular across different input representations, are scarce. We address this gap in the research landscape by a comprehensive benchmarking study covering three kinds of input representations, interpretable features, image representations and raw waveforms, across prototypical regression and classification use cases: blood pressure and atrial fibrillation prediction. In both cases, the best results are achieved by deep neural networks operating on raw time series as input representations. Within this model class, best results are achieved by modern convolutional neural networks (CNNs). but depending on the task setup, shallow CNNs are often also very competitive. We envision that these results will be insightful for researchers to guide their choice on machine learning tasks for PPG data, even beyond the use cases presented in this work.