This GitHub repository contains a comprehensive collection of resources related to a novel methodology for continuous estimation of arterial blood pressure using photoplethysmography (PPG) signals. The methodology is based on Deep Learning and aims to resist different types of distortion in the PPG signal, resulting in comparative results to previously presented papers in the field.
The proposed model has been rigorously evaluated and has been found to meet grade A in diastolic blood pressure (DBP) and mean arterial pressure (MAP) and grade B in systolic blood pressure (SBP) according to the British Hypertension Society (BHS) standard. Furthermore, it satisfies the Association for the Advancement of Medical Instrumentation (AAMI) standard conditions in SBP, DBP, and MAP.
Notably, this methodology represents a significant advancement as it is the first end-to-end PPG to ABP translating method that includes distorted PPG signals for blood pressure estimation. This innovation has the potential to significantly impact the field of blood pressure estimation and has implications for clinical practice and research.
The repository includes the code for the model, datasets used for training and evaluation, and any additional resources related to the research. This comprehensive collection of resources allows for transparency, reproducibility, and further advancement of the proposed methodology. Researchers, practitioners, and enthusiasts in the field can leverage these resources for further exploration, validation, and potential enhancement of the proposed methodology.