Key result
Tiny CNN trained on synthetic PPG matches complex algorithms for real-time heart rate detection.
Why the study?
Strict privacy regulations make gathering robust, bias-free, and suitably anonymized datasets for health technology machine learning difficult, time-consuming, and expensive.
Synthetic photoplethysmogram data can effectively train highly efficient edge machine learning models for accurate, real-time heart rate monitoring on wearable devices, bypassing privacy constraints associated with real patient data.
Answers are grounded in this paper and cite their sources.
May enable privacy-preserving tiny models for wearable HR monitoring; extends synthetic PPG utility but leaves validation open.
Strict privacy regulations pose challenges to the development of machine learning (ML) in the field of health technology where data is particularly sensitive. Gathering and using robust, bias-free, and suitably anonymized datasets required by ML models is difficult, time-consuming, and thus expensive. Parametric synthetic data offers a solution by mimicking real-world processes with easily adjustable parameters that shape the information content of the data as desired. This article presents a system demonstrating how synthetic data can be used in conjunction with wearable edge devices. Importantly, the system preserves privacy as there is no risk of leaking sensitive information from the model or during the use of the wearable device. The system consists of (1) a synthetic photoplethysmogram (PPG) model, (2) convolutional neural network (CNN) models trained with the synthetic signals, (3) a wearable edge device that computes heart rate from real-time PPG signals using the developed CNN models, and (4) an accompanying mobile phone application receiving the results. The synthetic model produces realistic PPG signals together with labels that can be used in CNN model training. The quality of the synthetic data is sufficient to train even a tiny CNN model with only two convolutional layers and 28 parameters to detect PPG waveform feet. The developed wearable device is able to run the model smoothly and the performance of the model is on par with the more complex models and other foot detection algorithms.
No takes yet. Share an insight, caveat, or question.
Sirkiä et al. (2023) studied this question. Wearable edge machine learning with synthetic PPGs vs. Traditional foot detection algorithms was evaluated on Heart rate mean absolute error (MAE) and foot detection F1 score. A tiny convolutional neural network model trained purely on synthetic photoplethysmogram data performed on par with more complex models and traditional algorithms for real-time heart rate detection.
Synapse has enriched 10 related papers. Consider them for comparative context: