A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis

Abstract

We undertook a systematic review of the diagnostic accuracy of artificial intelligence-based software for identification of radiologic abnormalities ( computer-aided detection , or CAD) compatible with pulmonary tuberculosis on chest x-rays (CXRs). We searched four databases for articles published between January 2005-February 2019. We summarized data on CAD type, study design, and diagnostic accuracy. We assessed risk of bias with QUADAS-2. We included 53 of the 4712 articles reviewed: 40 focused on CAD design methods (“Development” studies) and 13 focused on evaluation of CAD (“Clinical” studies). Meta-analyses were not performed due to methodological differences. Development studies were more likely to use CXR databases with greater potential for bias as compared to Clinical studies. Areas under the receiver operating characteristic curve (median AUC [IQR]) were significantly higher: in Development studies AUC: 0.88 [0.82–0.90]) versus Clinical studies (0.75 [0.66–0.87]; p-value 0.004); and with deep-learning (0.91 [0.88–0.99]) versus machine-learning (0.82 [0.75–0.89]; p = 0.001). We conclude that CAD programs are promising, but the majority of work thus far has been on development rather than clinical evaluation. We provide concrete suggestions on what study design elements should be improved.

Finding and Closing the Gaps in the Tuberculosis Elimination Campaign

“…The use of highly sensitive radiologic criteria has identified a high-risk population, but the expected lower specificity may result in some individuals being required to undergo unnecessary evaluation before departure and after arrival. One potential gap-closing option for improving the accuracy and efficiency of identifying TB cases that could be evaluated is the use of artificial-intelligence interpretation of chest radiographic screening findings ( 9 ). Perhaps the TB risk prediction among those with abnormal chest radiographs could be improved by the addition of predeparture interferon-γ release assay testing or other predictive tests under evaluation.…”

Operationalizing Mobile Computer-assisted TB Screening and Diagnosis With Wellness on Wheels (WoW)) in Nigeria: Balancing Feasibility and Iterative Efficiency

“…Publication bias has limited potential learning from the many active case finding projects with poor risk group targeting, scant community engagement, mediocre results or initial missteps [7]. Finally, few studies have been conducted independently from CAD software developers [8].…”

Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs

“…There are many AI algorithms that have already been developed for CXR applications (see review [18]) and these AI algorithms can be repurposed to study COVID-19 lung infection. A few studies have already reported AI applications to classify COVID-19 versus non-COVID-19 lung infection using CXR [19][20][21][22] and CT [23][24][25][26].…”