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

. 2019 Nov 14;9:16824. doi: 10.1038/s41598-019-53115-3

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

© The Author(s) 2019

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Classifier performance versus classifier confidence: The automatic sleep scoring algorithm also estimates the probability of the chosen label being correct. This may be interpreted as our ‘confidence’ in the scoring. (A) Median confidence for all assigned labels across each night relative to Cohen’s kappa for the same night. We see a clear trend of greater confidence across a whole recording corresponding to greater overall scoring performance. (B) Observed probability of a given epoch being correctly/incorrectly labeled, as a function of label confidence (plotted to left axis). ‘Conf. Distribution’ shows the distribution of epoch-level confidence estimates (plotted to right axis). As in (A), we see a clear trend of high confidence epochs generally being correctly labelled. Given an epoch of specific confidence we see that confidence has to be below 0.4 for the label to be most likely incorrect, and that most confidence estimates are above 0.5. Both graphs are based on leave-one-subject-out cross validation for 5-stage scoring.