Central Blood Pressure Estimation From Distal PPG Measurement Using Semiclassical Signal Analysis Features

Background and objective: Blood pressure (BP) is one of the crucial indicators that contains valuable medical information about cardiovascular activities. Developing photoplethysmography (PPG)-based cuffless BP estimation algorithms with enough robustness accuracy clinically useful in practice, due to its simplicity noninvasiveness. In this paper, we have developed tested two frameworks for arterial blood (ABP) at central arteries using electrocardiogram. Methods: Supervised learning, as adapted by most studies regarding topic, introduced comparing three machine learning algorithms. Features are extracted semi-classical signal analysis (SCSA) tools. To further increase estimation, another algorithm presented. A single feed-forward neural network (FFNN) utilized regression PPG features, which SCSA later used FFNN input. Both perform robustly against MIMIC II database guarantee statistical reliability. Results: We evaluated performance Advancement Medical Instrumentation (AAMI) British Hypertension Society (BHS) standards, compared standard deviation (STD) error current state arts. With AAMI standard, first method yields comparable existing literature values. Regarding BHS protocol, second achieves grade Conclusion: conclude combination informative features from Schrödinger's spectrum, can be non-invasively estimated a reliable accurate way. Furthermore, proposed could potentially enable applications development mobile healthcare device.