Continuous Cuffless Blood Pressure Estimation via Effective and Efficient Broad Learning Model

Hypertension is a major risk factor for cardiovascular diseases and all-cause mortality, making accessible and easy blood pressure (BP) measurement, such as cuffless methods, crucial for its prevention, detection, and management. Cuffless BP estimation using wearable cardiovascular signals via deep learning models (DLMs) offers a promising solution. However, implementation of the DLMs usually requires high computational cost and time. This study addresses these challenges by offering an end-to-end broad learning model (BLM) for effective and efficient cuffless BP estimation. The BLM increases network width rather than depth compared to DLMs, reducing computational complexity and improving training efficiency for continuous BP estimation. We also explore an incremental learning mode that provides high memory efficiency and flexibility. Validation of the proposed method on the University of California Irvine (UCI) database, which spanned 403.67 hours, demonstrated that the standard BLM (SBLM) achieves a mean absolute error (MAE) of 11.72 mmHg for the estimation of the arterial BP (ABP) waveform, which was comparable to the performance to DLMs, such as long short-term memory (LSTM) and the one-dimensional convolutional neural network (1D-CNN), while significantly improving training efficiency by 25.20 times. Furthermore, incremental BLM (IBLM) provides a horizontal scalability approach, which involves expanding the model by adding nodes in a single layer rather than increasing the number of layers, for incremental learning, effectively updating the model while maintaining comparable predictive performance. This approach reduces storage demands by supporting incremental learning with streaming or partial datasets. In addition, the mean absolute error (MAE) (mean error (ME) ± standard deviation (SD)) values of the SBLM for predicting systolic BP (SBP) and diastolic BP (DBP) were 3.04 mmHg (2.85 ± 4.15 mmHg) and 2.57 mmHg (-2.47 ± 3.03 mmHg). This study highlights the potential of BLM for personalized, real-time, and continuous cuffless BP monitoring, offering a practical solution for healthcare applications.