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 Oct 22;10:18120. doi: 10.1038/s41598-020-74648-y

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 licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence 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 licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Performance comparison between SUSPECT-RIF and the gold-standard GeneXpert-MTB/RIF. (A) The ROC curve shows superior performance of SUSPECT-RIF in successfully distinguishing between RIF-susceptible and resistant mutations on the M. tuberculosis dataset (n = 319) achieving an AUC of 0.95, significantly outperforming GeneXpert (AUC of 0.66, p-value < 2.2E-16). When comparing performance of the two tools across all the different validation datasets, through Accuracy (B), Sensitivity (C) and F1 Score (D) metrics, we show that SUSPECT-RIF significantly outperforms GeneXpert-MTB/RIF across all measures tested, and across all tests. Notably, the highest significance was for the was achieved for the large M. tuberculosis (n = 319) test, and the M. leprae (n = 42) tests. The least significant results across all metric tested were for Miotto et al.test, primarily because most of these mutations (90.6%) are present within the RRDR, showing comparable performance to the gold standard. As for the P. aeruginosa and S. aureus mutational sets, lower significance values across the metrics, leading to non-significance when considering F1 Score, is thought to be a direct result of sample size and proportion of mutations in RRDR (66.7% and 70.6% respectively). All significance tests were computed using a two-tailed z-test with continuity correction.