Detection of special points on a photoplethysmogram using MLPNN model

Abstract

Photoplethysmography is an up-to-date method of objective assessment of the state of regional blood flow, tone of arteries and veins. Quantitative estimates of vascular tone indicators are obtained by analyzing the contour of the photoplethysmogram within the pulse cycle. A new method for detecting singular points of the contour of photoplethysmograms, based on the model of a multilayer perceptronic neural network (MLPNN), is proposed. The effectiveness of the developed network for finding singular points - the systolic peak, dicrotic notch and diastolic rise of the photoplethysmogram - has been demonstrated. The average relative error in determining the special points does not exceed 5 percent. The proposed method can be used in computer monitoring systems of vascular tone.

File with abstract

Speaker

Vladislav Yurievich Gribkov
Volgograd State University
Russia

Discussion

Ask question