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 Apr 3;9:90. doi: 10.3389/fcimb.2019.00090

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

Copyright © 2019 Hu, Feng, Wu, Liu, Zhang, Hao, Liang, Li, Li, Lv, Xu, Zhu and Sun.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Random forest model to discriminate TB patients from healthy controls. (A) Five repeats of 10-fold cross-validation error. Relative abundances of 348 species in controls and patients (n = 31 and 30) were used to train the model. Each gray line indicates a repeat, and the red line indicated the average. The dashed line indicates the number of species in the optimal set, which was determined to be 3 species. (B) Random forest Mean Decrease in Accuracy and Gini. Red circles indicate the 3 species in the optimal set according to cross-validation in (A). (C) ROC for the training set. AUC = 0.846 and the 95% CI is 0.651–0.956 (controls, n = 31; patients, n = 30). (D) ROC for the testing set. AUC = 0.767 and the 95% CI is 0.614–0.920 (controls, n = 30; patients, n = 16).