Key result
The proposed TimePPG models achieved a Mean Absolute Error as low as 3.84 BPM on the PPG-Dalia dataset, outperforming previous state-of-the-art methods while remaining computationally efficient.
Why the study?
Existing PPG-based heart rate monitoring solutions are not robust against motion artifacts or rely heavily on hand-tuned parameters, leading to poor generalization performance.
A novel deep learning-based approach using Temporal Convolutional Networks enables highly accurate and energy-efficient heart rate monitoring from wrist-worn PPG sensors by effectively mitigating motion artifacts.
Supports efficient wearable PPG heart rate monitoring; leaves open clinical validation before practice adoption.
Photoplethysmography (PPG) sensors allow for non-invasive and comfortable heart rate (HR) monitoring, suitable for compact wrist-worn devices. Unfortunately, motion artifacts (MAs) severely impact the monitoring accuracy, causing high variability in the skin-to-sensor interface. Several data fusion techniques have been introduced to cope with this problem, based on combining PPG signals with inertial sensor data. Until now, both commercial and reasearch solutions are computationally efficient but not very robust, or strongly dependent on hand-tuned parameters, which leads to poor generalization performance. In this work, we tackle these limitations by proposing a computationally lightweight yet robust deep learning-based approach for PPG-based HR estimation. Specifically, we derive a diverse set of Temporal Convolutional Networks for HR estimation, leveraging Neural Architecture Search. Moreover, we also introduce ActPPG, an adaptive algorithm that selects among multiple HR estimators depending on the amount of MAs, to improve energy efficiency. We validate our approaches on two benchmark datasets, achieving as low as 3.84 beats per minute of Mean Absolute Error on PPG-Dalia, which outperforms the previous state of the art. Moreover, we deploy our models on a low-power commercial microcontroller (STM32L4), obtaining a rich set of Pareto optimal solutions in the complexity vs. accuracy space.
No takes yet. Share an insight, caveat, or question.
Burrello et al. (2022) studied Healthy subjects (Heart rate monitoring) (n=15). TimePPG (Temporal Convolutional Networks) and ActPPG vs. State-of-the-art algorithms was evaluated on Mean Absolute Error (MAE) of Heart Rate estimation. The proposed TimePPG models achieved a Mean Absolute Error as low as 3.84 BPM on the PPG-Dalia dataset, outperforming previous state-of-the-art methods while remaining computationally efficient.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: