Classification of Respiratory Diseases A non-contact application of depth-based plethysmography for classifying asthma, COPD and healthy subjects with individual correlation masks

Contactless measurement methods offer a novel approach to assessing respiratory parameters. This study investigates the feasibility of classifying chronic obstructive pulmonary disease, asthma, and healthy individuals using depth-based plethysmography (DPG). The approach involves calculating Pearson...

Full description

Saved in:
Bibliographic Details
Published inCurrent directions in biomedical engineering Vol. 10; no. 4; pp. 665 - 668
Main Authors Wichum, Felix, Wiede, Christian, Seidl, Karsten
Format Journal Article
LanguageEnglish
Published 01.12.2024
Online AccessGet full text

Cover

More Information
Summary:Contactless measurement methods offer a novel approach to assessing respiratory parameters. This study investigates the feasibility of classifying chronic obstructive pulmonary disease, asthma, and healthy individuals using depth-based plethysmography (DPG). The approach involves calculating Pearson's correlation coefficient for all pixel-wise signals against each other, with the cumulative result visualized in patient-specific masks. A convolutional neural network is used for the classification process. For evaluation, on a recorded data set (N=53), a classification accuracy of 57.7% and Cohen’s Kappa of 0.28 were reached. These findings provide indications that DPG might effectively classify respiratory conditions by analyzing respiratory motion dynamics.
ISSN:2364-5504
2364-5504
DOI:10.1515/cdbme-2024-2163