Blood Pressure Assessment with Differential Pulse Transit Time and Deep Learning: A Proof of Concept.

摘要: Background: Modern clinical environments are laden with technology devices continuously gathering physiological data from patients. This is especially true in critical care environments, where life-saving decisions may have to be made on the basis of signals monitoring devices. Hemodynamic essential dialysis, surgery, and critically ill For most severe patients, blood pressure normally assessed through a catheter, which an invasive procedure that result adverse effects. Blood can also monitored noninvasively different methods these used for continuous assessment using machine learning methods. Previous studies found pulse transit time related pressure. In this short paper, we propose study feasibility implementing data-driven model based restricted Boltzmann artificial neural networks, delivering first proof concept validity viability method prediction models. Summary Key Messages: patients (e.g., ill), catheters. Alternatively, noninvasive been developed its monitorization. Data obtained measurements study, network present prediction.