Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2020 Jan 4;20(1):286. doi: 10.3390/s20010286

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2020 by the authors.

Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

PMC Copyright notice

Predictive and diagnostic accuracy of the HRV features with regards to AHI, ODI and ESS. The predictive accuracy of the HRV features is provided by surface fitting applied to PCA (left panels). The isoclines (blue lines) superimposed to the PCA biplot display the linear relationship (trend surface) between HRV features and the responses (AHI, ODI, ESS; blue arrows). The diagnostic accuracy is shown by means of ROC curve displaying the sensitivity vs. false positive rate of a support vector machine-based AHI classifier (right panels). The curves are derived from ECG data obtained during PSG and ECG belt with or without data pre-filtering. The diagonal line indicates the random guess line. The dotted lines of the upper right panel cross at the optimal classification accuracy for AHI (AHI = 18 $h^{- 1}$ ).

Predictive and diagnostic accuracy of the HRV features with regards to AHI, ODI and ESS. The predictive accuracy of the HRV features is provided by surface fitting applied to PCA (left panels). The isoclines (blue lines) superimposed to the PCA biplot display the linear relationship (trend surface) between HRV features and the responses (AHI, ODI, ESS; blue arrows). The diagnostic accuracy is shown by means of ROC curve displaying the sensitivity vs. false positive rate of a support vector machine-based AHI classifier (right panels). The curves are derived from ECG data obtained during PSG and ECG belt with or without data pre-filtering. The diagonal line indicates the random guess line. The dotted lines of the upper right panel cross at the optimal classification accuracy for AHI (AHI = 18 $h^{- 1}$ ).