Continuous blood pressure assessment from a photoplethysmographic signal with Deep Belief Networks (LB674)

Abstract

Continuous blood pressure assessment from a photoplethysmographic signal with Deep Belief Networks Vicent J. Ribas Ripoll PhD; Anna Wojdel PhD; Anna Sáez de Tejada Cuenca; Juan C. Ruiz‐Rodríguez, MD; Adolf Ruiz‐Sanmartín, MD; Miriam de Nadal MD, PhD; Enrique Romero PhD; Alfredo Vellido PhD A prospective study was conducted at a critical care department and post‐anesthesia care unit of a university teaching hospital in Barcelona, Spain. The study recruited 707 patients with invasive BP and finger PPG waves over a period of 26 months. Exclusion criteria were presence of major arrhythmia, immediate death condition and disturbances in the arterial or PPG curve morphology. For each patient we automatically recorded the systolic blood pressure (SBP), mean arterial pressure (MAP), diastolic blood pressure (DBP) and PPG curve for 30 minutes. The PPG signal was further processed to obtain a set of features that were used to construct a Deep Belief Network with Gaussian Restricted Boltzmann Machine (DBN‐RBM). The available dataset was split into three subsets (Training, Validation and Testing). The training and validation datasets included 85% of data and the testing dataset included 15% of the available data. The regression error was assessed through a Bland‐Altman analysis and the AAMI standard. The mean prediction error were ‐2.98+‐19.35 mmHg for SBP, ‐3.38+‐10.35 mmHg for MAP and 3.65+‐8.69 mmHg for DBP.The results obtained are promising for the assessment of MAP and DBP with DBN‐RBM. Further research and clinical validation are needed to bring this technology to standard medical practice.Grant Funding Source: Supported by Shockomics (FP7 framework)