NABNet: A Nested Attention-guided BiConvLSTM network for a robust prediction of Blood Pressure components from reconstructed Arterial Blood Pressure waveforms using PPG and ECG signals. (January 2023)

• Record Type: Journal Article
• Authors: Mahmud, Sakib; Ibtehaz, Nabil; Khandakar, Amith; Sohel Rahman, M.; JR. Gonzales, Antonio; Rahman, Tawsifur; Shafayet Hossain, Md; Sakib Abrar Hossain, Md.; Ahasan Atick Faisal, Md.; Fuad Abir, Farhan; Musharavati, Farayi; E. H. Chowdhury, Muhammad
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 2
• Publication Date: 2023-01
• Subjects: NABNet -- Arterial Blood Pressure (ABP) -- Photoplethysmogram (PPG) -- Electrocardiogram (ECG) -- BP Prediction -- ABP Estimation -- Signal to Signal Synthesis -- Signal Reconstruction -- Guided Attention -- Bidirectional Convolutional LSTM -- 1D-Segmentation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104247
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Proposed NABNet Model Architecture. Highlights: Unlike traditional BP prediction schemes, we aim at estimating ABP waveforms from PPG and ECG signals from which all BP information is extracted. We propose a hybrid pipeline that separates the ABP estimation process into two parts viz. BP prediction and ABP estimation. The predicted normalized ABP waveforms are linearly transformed into ABP signals using their respective BP metrics. We propose the NABNet architecture which utilizes Convolutional LSTM and Attention Guidance concepts for improving construction error accumulating due to ABP phase lag during segmentation. This study performs multiple sets of experiments to determine the best segmentation model for ABP estimation. The model is trained on a large, variable dataset with highly varying PPG and ECG waveforms to enhance the robustness and generalizability of the model. Abstract: Background: and Motivations: Continuous Blood Pressure (BP) monitoring is crucial for real-time health tracking, especially for people with hypertension and cardiovascular diseases (CVDs). The current cuff-based BP monitoring methods are non-invasive but discontinuous while continuous BP monitoring methods are mostly invasive and can only be applied in a clinical setup to patients being monitored by advanced equipment and medical experts. Several studies have reported different techniques for predicting BP values from non-invasive Photoplethysmogram (PPG) and Electrocardiogram (ECG) signals. Apart from BP readings, estimating ABP waveforms from non-invasive signals can provide vital body parameters such as Mean Arterial Pressure (MAP) which can be used to determine poor organ perfusion, nutrient supply to organs, and cardiovascular diseases (CVDs), etc. Methods: It is challenging to estimate ABP waveforms while maintaining a high BP prediction performance and ABP waveform pattern. In this work, we propose a novel approach for ABP waveform estimation by separating the task into BP prediction and a normalized ABP waveform estimation through segmentation from PPG, PPG derivatives, and ECG signals, and combining afterward. We propose the Nested Attention-guided BiConvLSTM Network or NABNet which uses LSTM blocks during segmentation for better handling of the existing phase shifts between PPG, ECG, and ABP signals. Several experiments were performed to improve the ABP reconstruction performance, which was combined with an existing BP prediction pipeline for the non-invasive estimation of ABP waveforms. Results: The proposed framework can robustly estimate ABP waveforms from PPG and ECG signals by reaching a high MAP performance and low construction error while maintaining the overall Grade A performance of the BP prediction pipeline. Conclusion: Linearly translating the range-normalized, synthesized ABP segments by corresponding SBP and DBP predictions from the BP prediction pipeline managed to robustly estimate ABP waveforms from PPG and ECG signals.