Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914242056159232 |
|---|---|
| author | Liang, Zequan Zhang, Ruoyu Shao, Wei Karthik, krishna Kourkchi, Ehsan Rafatirad, Setareh Homayoun, Houman |
| author_facet | Liang, Zequan Zhang, Ruoyu Shao, Wei Karthik, krishna Kourkchi, Ehsan Rafatirad, Setareh Homayoun, Houman |
| contents | Blood oxygen saturation (SpO2) is a vital marker for healthcare monitoring. Traditional SpO2 estimation methods often rely on complex clinical calibration, making them unsuitable for low-power, wearable applications. In this paper, we propose a transfer learning-based framework for the rapid adaptation of SpO2 estimation to energy-efficient wearable devices using low-sampling-rate (25Hz) dual-channel photoplethysmography (PPG). We first pretrain a bidirectional Long Short-Term Memory (BiLSTM) model with self-attention on a public clinical dataset, then fine-tune it using data collected from our wearable We-Be band and an FDA-approved reference pulse oximeter. Experimental results show that our approach achieves a mean absolute error (MAE) of 2.967% on the public dataset and 2.624% on the private dataset, significantly outperforming traditional calibration and non-transferred machine learning baselines. Moreover, using 25Hz PPG reduces power consumption by 40% compared to 100Hz, excluding baseline draw. Our method also attains an MAE of 3.284% in instantaneous SpO2 prediction, effectively capturing rapid fluctuations. These results demonstrate the rapid adaptation of accurate, low-power SpO2 monitoring on wearable devices without the need for clinical calibration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12515 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG Liang, Zequan Zhang, Ruoyu Shao, Wei Karthik, krishna Kourkchi, Ehsan Rafatirad, Setareh Homayoun, Houman Signal Processing Machine Learning Blood oxygen saturation (SpO2) is a vital marker for healthcare monitoring. Traditional SpO2 estimation methods often rely on complex clinical calibration, making them unsuitable for low-power, wearable applications. In this paper, we propose a transfer learning-based framework for the rapid adaptation of SpO2 estimation to energy-efficient wearable devices using low-sampling-rate (25Hz) dual-channel photoplethysmography (PPG). We first pretrain a bidirectional Long Short-Term Memory (BiLSTM) model with self-attention on a public clinical dataset, then fine-tune it using data collected from our wearable We-Be band and an FDA-approved reference pulse oximeter. Experimental results show that our approach achieves a mean absolute error (MAE) of 2.967% on the public dataset and 2.624% on the private dataset, significantly outperforming traditional calibration and non-transferred machine learning baselines. Moreover, using 25Hz PPG reduces power consumption by 40% compared to 100Hz, excluding baseline draw. Our method also attains an MAE of 3.284% in instantaneous SpO2 prediction, effectively capturing rapid fluctuations. These results demonstrate the rapid adaptation of accurate, low-power SpO2 monitoring on wearable devices without the need for clinical calibration. |
| title | Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2509.12515 |