Unobtrusive and Continuous Measurements of Dynamic Beat-to-beat Blood Pressure Using Multimodal Physiological Signals
Published in IEEE Journal of Biomedical and Health Informatics (JBHI), 2024
McBP-Net, a deep learning model using a hybrid CNN-LSTM architecture with multimodal signals and handcrafted features, significantly improves the accuracy of continuous beat-to-beat blood pressure estimation, achieving promising results for wearable cuffless BP measurements and outperforming existing methods in both accuracy and computational efficiency.