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 Dec 8;6:36. doi: 10.1038/s41531-020-00135-w

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

© The Author(s) 2020

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

Fig. 2 — The mean leave-one-subject-out cross-validation (LOSO-CV) classification accuracy of the smartphone-based prediction of the blinded MDS-UPDRS III. The accuracy of a number of approaches is compared to a random baseline (similar to rolling a dice where subjects were randomly assigned to a clinical category). The fully pre-specified analysis (blue) relied on pre-published features and a standard multinomial regression model. The Best Classifier approach selected the best classifier from a range based on best performance but used only the pre-specified features. The Best Feature approach selected the best feature from a range but used only the pre-specified classifier. The Best Classifier and Feature approach selected the best combination of both. Approaches are graded according to the risk of selection bias: the pre-specified analysis has a very low risk, the Best Classifier or Best Feature analyses have low risk whilst the combination approach has a moderate risk of over-optimistic accuracy. Error bars represent SEM.