TY - GEN
T1 - Deep learning model with individualized fine-tuning for dynamic and beat-to-beat blood pressure estimation
AU - Hong, Jingyuan
AU - Gao, Jiasheng
AU - Liu, Qing
AU - Zhang, Yuanting
AU - Zheng, Yali
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/27
Y1 - 2021/7/27
N2 - Deep learning (DL) models have demonstrated great potential in cuffless blood pressure (BP) estimation under static conditions, while the performance under dynamic conditions was still not fully validated. This study developed a DL model using population data for training and followed by individualized fine-tuning to directly learn features from multi-sensory signals including electrocardiogram (ECG), photoplethysmogram (PPG) and PPG derivatives for beat-to-beat BP estimation under water drinking. 25 healthy subjects were recruited, and the leave-one-subject-out approach was used to evaluate the model performance. The results showed that individualized fine-tuning using a small amount of individual baseline data did not change the tracking capability of the model, while can largely reduce the individual bias in dynamic BP estimation, with the mean absolute errors decreased from 13.43 to 9.49 mmHg and 8.48 to 5.54 mmHg for systolic BP and diastolic BP, respectively. It was also found that the model presented better results around the baseline BP levels than that at larger deviations from the baseline, indicating that future work should incorporate individual dynamic data in the fine-tuning to improve dynamic BP estimation further.
AB - Deep learning (DL) models have demonstrated great potential in cuffless blood pressure (BP) estimation under static conditions, while the performance under dynamic conditions was still not fully validated. This study developed a DL model using population data for training and followed by individualized fine-tuning to directly learn features from multi-sensory signals including electrocardiogram (ECG), photoplethysmogram (PPG) and PPG derivatives for beat-to-beat BP estimation under water drinking. 25 healthy subjects were recruited, and the leave-one-subject-out approach was used to evaluate the model performance. The results showed that individualized fine-tuning using a small amount of individual baseline data did not change the tracking capability of the model, while can largely reduce the individual bias in dynamic BP estimation, with the mean absolute errors decreased from 13.43 to 9.49 mmHg and 8.48 to 5.54 mmHg for systolic BP and diastolic BP, respectively. It was also found that the model presented better results around the baseline BP levels than that at larger deviations from the baseline, indicating that future work should incorporate individual dynamic data in the fine-tuning to improve dynamic BP estimation further.
KW - Cuff-less and beat-to-beat blood pressure estimation
KW - Deep learning
KW - Dynamic conditions
KW - Fine-tuning
UR - http://www.scopus.com/inward/record.url?scp=85120686171&partnerID=8YFLogxK
U2 - 10.1109/BSN51625.2021.9507019
DO - 10.1109/BSN51625.2021.9507019
M3 - Conference Proceeding
AN - SCOPUS:85120686171
T3 - 2021 IEEE 17th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2021
BT - 2021 IEEE 17th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks, BSN 2021
Y2 - 27 July 2021 through 30 July 2021
ER -