Feng Yang1, Hang Yu1, Karthik Kantipudi2, Manohar Karki1, Yasmin M Kassim1, Alex Rosenthal2, Darrell E Hurt2, Ziv Yaniv2, Stefan Jaeger1. 1. Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA. 2. Office of Cyber Infrastructure and Computational Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, USA.
Abstract
BACKGROUND: Tuberculosis (TB) drug resistance is a worldwide public health problem that threatens progress made in TB care and control. Early detection of drug resistance is important for disease control, with discrimination between drug-resistant TB (DR-TB) and drug-sensitive TB (DS-TB) still being an open problem. The objective of this work is to investigate the relevance of readily available clinical data and data derived from chest X-rays (CXRs) in DR-TB prediction and to investigate the possibility of applying machine learning techniques to selected clinical and radiological features for discrimination between DR-TB and DS-TB. We hypothesize that the number of sextants affected by abnormalities such as nodule, cavity, collapse and infiltrate may serve as a radiological feature for DR-TB identification, and that both clinical and radiological features are important factors for machine classification of DR-TB and DS-TB. METHODS: We use data from the NIAID TB Portals program (https://tbportals.niaid.nih.gov), 1,455 DR-TB cases and 782 DS-TB cases from 11 countries. We first select three clinical features and 26 radiological features from the dataset. Then, we perform Pearson's chi-squared test to analyze the significance of the selected clinical and radiological features. Finally, we train machine classifiers based on different features and evaluate their ability to differentiate between DR-TB and DS-TB. RESULTS: Pearson's chi-squared test shows that two clinical features and 23 radiological features are statistically significant regarding DR-TB vs. DS-TB. A ten-fold cross-validation using a support vector machine shows that automatic discrimination between DR-TB and DS-TB achieves an average accuracy of 72.34% and an average AUC value of 78.42%, when combing all 25 statistically significant features. CONCLUSIONS: Our study suggests that the number of affected lung sextants can be used for predicting DR-TB, and that automatic discrimination between DR-TB and DS-TB is possible, with a combination of clinical features and radiological features providing the best performance. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: Tuberculosis (TB) drug resistance is a worldwide public health problem that threatens progress made in TB care and control. Early detection of drug resistance is important for disease control, with discrimination between drug-resistant TB (DR-TB) and drug-sensitive TB (DS-TB) still being an open problem. The objective of this work is to investigate the relevance of readily available clinical data and data derived from chest X-rays (CXRs) in DR-TB prediction and to investigate the possibility of applying machine learning techniques to selected clinical and radiological features for discrimination between DR-TB and DS-TB. We hypothesize that the number of sextants affected by abnormalities such as nodule, cavity, collapse and infiltrate may serve as a radiological feature for DR-TB identification, and that both clinical and radiological features are important factors for machine classification of DR-TB and DS-TB. METHODS: We use data from the NIAID TB Portals program (https://tbportals.niaid.nih.gov), 1,455 DR-TB cases and 782 DS-TB cases from 11 countries. We first select three clinical features and 26 radiological features from the dataset. Then, we perform Pearson's chi-squared test to analyze the significance of the selected clinical and radiological features. Finally, we train machine classifiers based on different features and evaluate their ability to differentiate between DR-TB and DS-TB. RESULTS: Pearson's chi-squared test shows that two clinical features and 23 radiological features are statistically significant regarding DR-TB vs. DS-TB. A ten-fold cross-validation using a support vector machine shows that automatic discrimination between DR-TB and DS-TB achieves an average accuracy of 72.34% and an average AUC value of 78.42%, when combing all 25 statistically significant features. CONCLUSIONS: Our study suggests that the number of affected lung sextants can be used for predicting DR-TB, and that automatic discrimination between DR-TB and DS-TB is possible, with a combination of clinical features and radiological features providing the best performance. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Authors: Xinyu Zhang; Aase B Andersen; Troels Lillebaek; Zaza Kamper-Jørgensen; Vibeke Østergaard Thomsen; Karin Ladefoged; Carl F Marrs; Lixin Zhang; Zhenhua Yang Journal: Am J Trop Med Hyg Date: 2011-08 Impact factor: 2.345
Authors: Max R O'Donnell; Jennifer Zelnick; Lise Werner; Iqbal Master; Marian Loveday; C Robert Horsburgh; Nesri Padayatchi Journal: Emerg Infect Dis Date: 2011-10 Impact factor: 6.883
Authors: Jan Heyckendorf; Sönke Andres; Claudio U Köser; Ioana D Olaru; Thomas Schön; Erik Sturegård; Patrick Beckert; Viola Schleusener; Thomas A Kohl; Doris Hillemann; Danesh Moradigaravand; Julian Parkhill; Sharon J Peacock; Stefan Niemann; Christoph Lange; Matthias Merker Journal: Antimicrob Agents Chemother Date: 2018-01-25 Impact factor: 5.191
Authors: M E Murphy; G H Wills; S Murthy; C Louw; A L C Bateson; R D Hunt; T D McHugh; A J Nunn; S K Meredith; C M Mendel; M Spigelman; A M Crook; S H Gillespie Journal: BMC Med Date: 2018-10-17 Impact factor: 8.775
Authors: Kurt R Wollenberg; Brendan M Jeffrey; Michael A Harris; Andrei Gabrielian; Darrell E Hurt; Alex Rosenthal Journal: Tuberculosis (Edinb) Date: 2022-01-24 Impact factor: 3.131