Similar performances but markedly different triaging thresholds in three CAD4TB versions risk systematic errors in TB screening programs
Fehr, J.; Wong, E. B.
Show abstract
Tuberculosis (TB) screening programs may apply computer-aided diagnostic (CAD) tools on chest radiographs to select people for microbiological sputum examination using a pre-selected triaging threshold. CAD software-updates are frequently introduced and it is unknown whether their use requires adjustment of triaging thresholds. In a community-based screening program in South Africa, we compared the scores between the three recent CAD4TB versions (v5, v6, and v7) and assessed their performance to identify microbiologically-confirmed TB. The performance of all versions was similar (v5: AUC 0.78, v6: AUC 0.79, v7: AUC 0.80; p-values>0.05), but along a 0-100 point scale, each had markedly different score distributions and optimal triaging thresholds (v5: 40, v6: 47, v7: 20). This has the potential to cause confusion within TB screening programs as these tools are increasingly adopted and new versions released. Independent guidance for adapting CAD triaging thresholds for frequently released software updates is needed.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development and Validation of a Deep Learning Model for Detecting Signs of Tuberculosis on Chest Radiographs among US-bound Immigrants and Refugees 96%
- A Comparison of CXR-CAD Software to Radiologists in Identifying COVID-19 in Individuals Evaluated for Sars CoV 2 Infection in Malawi and Zambia 94%
- Implementation, feasibility, and acceptability of 99DOTS-based supervision of treatment for drug-susceptible TB in Uganda 93%
Similar papers in this journal
- Programmatic diagnostic accuracy and clinical utility of Xpert MTB/XDR in patients with rifampicin-resistant tuberculosis in Georgia 94%
- Accelerating cough-based algorithms for pulmonary tuberculosis screening: Results from the CODA TB DREAM Challenge 93%
- C-reactive protein for pulmonary tuberculosis screening and treatment response monitoring in children 93%
Similar papers in this journal
- Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: analysis of an international, multicenter migrants screening study 96%
- Accuracy of digital chest x-ray analysis with artificial intelligence software as a triage and screening tool in hospitalized patients being evaluated for tuberculosis in Lima, Peru 96%
- Diagnostic accuracy study of the multiplex Truenat MTB Ultima/COVID-19 assay for simultaneous detection of Tuberculosis and SARS-CoV2 (COVID-19) 94%
Similar papers in this journal
- Diagnostic accuracy of swab-based molecular tests for tuberculosis using novel near point-of-care platforms: A multi-country evaluation 95%
- An observational study identifying highly tuberculosis-exposed, HIV-1-positive but persistently TB, tuberculin and IGRA negative persons with M. tuberculosis specific antibodies in Cape Town, South Africa 90%
- Accuracy of four lateral flow immunoassays for anti SARS-CoV-2 antibodies: a head-to-head comparative study 89%
Similar papers in this journal
- Adequacy of serial self-performed SARS-CoV-2 rapid antigen-detection testing for longitudinal mass screening in the workplace 91%
- Evaluation of an artificial intelligence model for detection of pneumothorax and tension pneumothorax on chest radiograph 89%
- Self-Reported Mask Wearing Greatly Exceeds Directly Observed Use: Urgent Need for Policy Intervention in Kenya 88%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.