A random forest model (RF) has similar accuracy to a support vector machine (SVM) for distinguishing patients with obstructive sleep apnea (OSA), according to a study published online Oct.
Bo Pang, of the University of California, Los Angeles, and colleagues examined whether using faster and less complex machine learning models, including SVM and RF, with brain diffusion tensor imaging (DTI) data could distinguish OSA from healthy controls. Two DTI series were obtained from 59 patients with OSA and 96 controls using 3.0-Tesla. Magnetic Resonance photogrammetry scanner Diffusion maps from each series were averaged using DTI data and were reorganized, averaged, normalized to a common space and used to perform cross-validation for model training, selection, and OSA prediction.
The researchers found that the RF model exhibited a classification accuracy of 0.73 for OSA and controls and an area under the curve value (AUC) on the receiver operator curve of 0.85. Cross-validation showed a similar fitting of the RF model with the SVM of OSA and control data (precision, 0.77; AUC, 0.84).
“OSA scanning can be faster and less complicated using Brain diffusion tensor imaging Data and machine learning. Such use of neuroimaging data and machine learning It will allow early screening for sleep apnea and intervention that can eventually help restore brain tissue changes and function,” the authors wrote.
Bo Pang et al, A machine learning approach to examining obstructive sleep apnea using brain diffusion tensor imaging, sleep research journal (2022). DOI: 10.1111 / jsr.13729
2022 Health Day. All rights reserved.
the quote: AI Model That Can Diagnose Obstructive Sleep Apnea (2022, Oct 20), Retrieved Oct 20, 2022 from https://medicalxpress.com/news/2022-10-ai-obstructive-apnea.html
This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.
