Interdisciplinary Program in Bioengineering, Seoul National University, Seoul 03080, Korea.
Institute of Medical and Biological Engineering, Medical Research Center, Seoul National University, Seoul 03080, Korea.
Sensors (Basel). 2020 Dec 25;21(1):96. doi: 10.3390/s21010096.
Continuous blood pressure (BP) monitoring is important for patients with hypertension. However, BP measurement with a cuff may be cumbersome for the patient. To overcome this limitation, various studies have suggested cuffless BP estimation models using deep learning algorithms. A generalized model should be considered to decrease the training time, and the model reproducibility should be taken into account in multi-day scenarios. In this study, a BP estimation model with a bidirectional long short-term memory network is proposed. The features are extracted from the electrocardiogram, photoplethysmogram, and ballistocardiogram. The leave-one-subject-out (LOSO) method is incorporated to generalize the model and fine-tuning is applied. The model was evaluated using one-day and multi-day tests. The proposed model achieved a mean absolute error (MAE) of 2.56 and 2.05 mmHg for the systolic and diastolic BP (SBP and DBP), respectively, in the one-day test. Moreover, the results demonstrated that the LOSO method with fine-tuning was more compatible in the multi-day test. The MAE values of the model were 5.82 and 5.24 mmHg for the SBP and DBP, respectively.
连续血压（BP）监测对高血压患者很重要。然而，袖带式血压测量可能会给患者带来不便。为了克服这一限制，许多研究提出了使用深度学习算法的无袖带血压估计模型。应考虑使用广义模型来减少训练时间，并在多日情况下考虑模型的可重复性。在这项研究中，提出了一种基于双向长短时记忆网络的 BP 估计模型。从心电图、光体积描记图和冲击描记图中提取特征。采用留一受试者法（LOSO）对模型进行泛化和微调。使用单日和多日测试对模型进行评估。该模型在单日测试中，收缩压（SBP）和舒张压（DBP）的平均绝对误差（MAE）分别为 2.56mmHg 和 2.05mmHg。此外，结果表明，具有微调功能的 LOSO 方法在多日测试中更具兼容性。模型的 SBP 和 DBP 的 MAE 值分别为 5.82mmHg 和 5.24mmHg。
