Key result
A deep neural network using pre-training and partial fine-tuning estimated systolic and diastolic blood pressure from PPG signals with mean absolute errors of 3.21 mmHg and 1.80 mmHg, respectively.
Why the study?
Existing neural network-based blood pressure estimation methods have practical shortcomings, including low estimation accuracy and poor model generalization.
Does a deep convolutional bidirectional recurrent neural network with pre-training and partial fine-tuning improve the accuracy of non-invasive blood pressure estimation using PPG signals?
Does a deep convolutional bidirectional recurrent neural network with pre-training and partial fine-tuning improve the accuracy of non-invasive blood pressure estimation using PPG signals?
A deep learning approach using pre-training and partial fine-tuning on PPG signals provides highly accurate non-invasive blood pressure estimation meeting AAMI and BHS standards.
Proposed PPG-based BP estimation requires prospective validation before clinical use; leaves open routine adoption pending accuracy confirmation.
Objective . Daily blood pressure (BP) monitoring is essential since BP levels can reflect the functions of heart pumping and vasoconstriction. Although various neural network-based BP estimate approaches have been proposed, they have certain practical shortcomings, such as low estimation accuracy and poor model generalization. Based on the strategy of pre-training and partial fine-tuning, this work proposes a non-invasive method for BP estimation using the photoplethysmography (PPG) signal. Approach . To learn the PPG-BP relationship, the deep convolutional bidirectional recurrent neural network (DC-Bi-RNN) was pre-trained with data from the public medical information mark for intensive care (MIMIC III) database. A tiny quantity of data from the target subject was used to fine-tune the specific layers of the pre-trained model to learn more individual-specific information to achieve highly accurate BP estimation. Main results. The mean absolute error and the Pearson correlation coefficient ( r ) of the proposed algorithm are 3.21 mmHg and 0.919 for systolic BP, and 1.80 mmHg and 0.898 for diastolic BP (DBP). The experimental results show that our method outperforms other methods and meets the requirements of the Association for the Advancement of Medical Instrumentation standard, and received an A grade according to the British Hypertension Society standard. Significance. The proposed method applies the strategy of pre-training and partial fine-tuning to BP estimation and verifies its effectiveness in improving the accuracy of non-invasive BP estimation.
No takes yet. Share an insight, caveat, or question.
Meng et al. (2022) studied Blood pressure estimation. Deep convolutional bidirectional recurrent neural network (DC-Bi-RNN) with pre-training and partial fine-tuning vs. Other methods was evaluated on Mean absolute error and Pearson correlation coefficient for systolic and diastolic BP. A deep neural network using pre-training and partial fine-tuning estimated systolic and diastolic blood pressure from PPG signals with mean absolute errors of 3.21 mmHg and 1.80 mmHg, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: