Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis

Abstract

Computer-aided detection (CAD) was recently recommended by the WHO for TB screening and triage based on several evaluations, but unlike traditional diagnostic tests, software versions are updated frequently and require constant evaluation. Since then, newer versions of two of the evaluated products have already been released. We used a case control sample of 12,890 chest X-rays to compare performance and model the programmatic effect of upgrading to newer versions of CAD4TB and qXR. We compared the area under the receiver operating characteristic curve (AUC), overall, and with data stratified by age, TB history, gender, and patient source. All versions were compared against radiologist readings and WHO’s Target Product Profile (TPP) for a TB triage test. Both newer versions significantly outperformed their predecessors in terms of AUC: CAD4TB version 6 (0.823 [0.816–0.830]), version 7 (0.903 [0.897–0.908]) and qXR version 2 (0.872 [0.866–0.878]), version 3 (0.906 [0.901–0.911]). Newer versions met WHO TPP values, older versions did not. All products equalled or surpassed the human radiologist performance with improvements in triage ability in newer versions. Humans and CAD performed worse in older age groups and among those with TB history. New versions of CAD outperform their predecessors. Prior to implementation CAD should be evaluated using local data because underlying neural networks can differ significantly. An independent rapid evaluation centre is necessitated to provide implementers with performance data on new versions of CAD products as they are developed.

The rise of artificial intelligence reading of chest X-rays for enhanced TB diagnosis and elimination

“…Whether these newer versions guarantee enhanced accuracy remains to be determined. Two recent studies compared the performance of newer versions of qXR 14 and CAD4TB 14 , 16 with their predecessors. In both, the updated CAD versions outperformed the preceding products, demonstrating the need for continuous reassessment and objective re-validation of diagnostic accuracy and threshold calibrations.…”

CAD4TB software updates: different triaging thresholds require caution by users and regulation by authorities

“… 2 – 7 CAD4TB is updated annually, and the 7 th version has been released recently. Screening programmes might be eager to use new versions because studies report improved performance, 8 , 9 but no recommendations on adopting software updates currently exist. Here, we have evaluated the triaging performance characteristics and optimal thresholds of the latest version of CAD4TB (v7) compared to the two most recent versions (v5 and v6).…”

Diagnostic Accuracy of Computer-Aided Detection During Active Case Finding for Pulmonary Tuberculosis in Africa: A Systematic Review and Meta-analysis

“…However, importantly, no meta-analyses or pooled estimates of accuracy were performed. Furthermore, observational studies outside of Africa evaluating CAD during active case finding have found the tool to be reasonably accurate (AUC >0.80), equaling or surpassing human reader performance [ 35 , 36 ].…”