A random forest (RF) model has similar accuracy to a support vector machine (SVM) for distinguishing patients with obstructive sleep apnea (OSA), according to a study published online Oct. 12 in Journal of Sleep Research.
Bo Pang of the University of California, Los Angeles, and colleagues investigated whether using faster and less complicated machine learning models, including SVM and RF, with brain diffusion tensor imaging (DTI) data can distinguish OSA from healthy controls. Two DTI series from 59 patients with OSA and 96 controls were obtained using a 3.0 Tesla magnetic resonance imaging scanner. Mean diffusivity maps were computed from each series using DTI data and realigned and averaged, normalized to a common space, and used to cross-validate for model training and selection, and for OSA prediction.
The researchers found that the HF model showed a classification accuracy of 0.73 for OSA and controls and an area under the curve (AUC) on the receiver-operator curve of 0.85. Cross-validation showed a comparable fit for the RF model with SVM for OSA and control data (accuracy 0.77; AUC 0.84).
“OSA screening can be faster and less complicated by using brain diffusion tensor imaging data and machine learning. Such use of neuroimaging data and machine learning will enable early OSA screening and intervention that may ultimately help restore brain tissue changes and function,” the authors write.
AI could improve the diagnostic accuracy of dynamic contrast-enhanced magnetic resonance imaging of the breast
Bo Pang et al, Machine learning approach for screening for obstructive sleep apnea using brain diffusion tensor imaging, Journal of Sleep Research (2022). DOI: 10.1111/jsr.13729
Health Day 2022. All rights reserved.
Citation: AI model can diagnose obstructive sleep apnea (2022, October 20), retrieved October 20, 2022 from https://medicalxpress.com/news/2022-10-ai-obstructive-apnea.html
This document is protected by copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is for informational purposes only.