An independent, multi-country head-to-head accuracy comparison of automated chest x-ray algorithms for the triage of pulmonary tuberculosis.

Autor:	Worodria W; 1. World Alliance for Lung and Intensive Care in Uganda, Kampala, Uganda., Castro R; 2. Division of Pulmonary and Critical Care Medicine, University of California, San Francisco, San Francisco, USA.; 3. Center for Tuberculosis, University of California, San Francisco, USA., Kik SV; 4. FIND, Geneva, Switzerland., Dalay V; 5. De La Salle Medical and Health Sciences Institute, Dasmarinas Cavite, Philippines., Derendinger B; 6. DSI-NRF Centre of Excellence for Biomedical Tuberculosis Research, South African Medical Research Council Centre for Tuberculosis Research, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, Stellenbosch University, South Africa., Festo C; 7. Ifakara Health Institute, Dar es Salaam, Tanzania., Nguyen TQ; 8. Vietnam National Tuberculosis Programme, National Lung Hospital, Hanoi, Vietnam.; 9. VNU University of Medicine and Pharmacy, Hanoi, Vietnam., Raberahona M; 10. Department of Infectious Diseases, CHU Joseph Raseta Befelatanana, Antananarivo, Madagascar.; 11. Centre d'Infectiologie Charles Mérieux, Université d'Antananarivo, Antananarivo, Madagascar., Sudarsan S; 2. Division of Pulmonary and Critical Care Medicine, University of California, San Francisco, San Francisco, USA.; 3. Center for Tuberculosis, University of California, San Francisco, USA., Andama A; 1. World Alliance for Lung and Intensive Care in Uganda, Kampala, Uganda., Thangakunam B; 12. Department of Pulmonary Medicine, Christian Medical College, Vellore, Tamil Nadu, India., Lyimo I; 7. Ifakara Health Institute, Dar es Salaam, Tanzania., Nguyen VN; 8. Vietnam National Tuberculosis Programme, National Lung Hospital, Hanoi, Vietnam.; 9. VNU University of Medicine and Pharmacy, Hanoi, Vietnam., Rakotoarivelo R; 11. Centre d'Infectiologie Charles Mérieux, Université d'Antananarivo, Antananarivo, Madagascar.; 13. Faculté de Médecine, Université de Fianarantsoa, Fianarantsoa, Madagascar., Theron G; 6. DSI-NRF Centre of Excellence for Biomedical Tuberculosis Research, South African Medical Research Council Centre for Tuberculosis Research, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, Stellenbosch University, South Africa., Yu C; 5. De La Salle Medical and Health Sciences Institute, Dasmarinas Cavite, Philippines., Denkinger CM; 14. Department of Infectious Disease and Tropical Medicine, Center for Infectious Diseases, Heidelberg University Hospital, Heidelberg, Germany.; 15. German Center for Infection Research, partner site, Heidelberg, Germany., Lapierre SG; 16. Centre de Recherche du Centre Hospitalier de l'Université de Montréal, Immunopathology Axis, Montréal, Canada.; 17. Université de Montréal, Department of Microbiology, Infectious Diseases and Immunology, Montréal, Canada., Cattamanchi A; 3. Center for Tuberculosis, University of California, San Francisco, USA.; 18. Division of Pulmonary Diseases and Critical Care Medicine, School of Medicine, University of California Irvine, Orange, USA., Christopher DJ; 10. Department of Infectious Diseases, CHU Joseph Raseta Befelatanana, Antananarivo, Madagascar., Jaganath D; 3. Center for Tuberculosis, University of California, San Francisco, USA.; 19. Division of Pediatric Infectious Diseases, University of California, San Francisco, San Francisco, USA.
Jazyk:	angličtina
Zdroj:	MedRxiv : the preprint server for health sciences [medRxiv] 2024 Jun 19. Date of Electronic Publication: 2024 Jun 19.
DOI:	10.1101/2024.06.19.24309061
Abstrakt:	Background: Computer-aided detection (CAD) algorithms for automated chest X-ray (CXR) reading have been endorsed by the World Health Organization for tuberculosis (TB) triage, but independent, multi-country assessment and comparison of current products are needed to guide implementation. Methods: We conducted a head-to-head evaluation of five CAD algorithms for TB triage across seven countries. We included CXRs from adults who presented to outpatient facilities with at least two weeks of cough in India, Madagascar, the Philippines, South Africa, Tanzania, Uganda, and Vietnam. The participants completed a standard evaluation for pulmonary TB, including sputum collection for Xpert MTB/RIF Ultra and culture. Against a microbiological reference standard, we calculated and compared the accuracy overall, by country and key groups for five CAD algorithms: CAD4TB (Delft Imaging), INSIGHT CXR (Lunit), DrAid (Vinbrain), Genki (Deeptek), and qXR (qure.AI). We determined the area under the ROC curve (AUC) and if any CAD product could achieve the minimum target accuracy for a TB triage test (≥90% sensitivity and ≥70% specificity). We then applied country- and population-specific thresholds and recalculated accuracy to assess any improvement in performance. Results: Of 3,927 individuals included, the median age was 41 years (IQR 29-54), 12.9% were people living with HIV (PLWH), 8.2% living with diabetes, and 21.2% had a prior history of TB. The overall AUC ranged from 0.774-0.819, and specificity ranged from 64.8-73.8% at 90% sensitivity. CAD4TB had the highest overall accuracy (73.8% specific, 95% CI 72.2-75.4, at 90% sensitivity), although qXR and INSIGHT CXR also achieved the target 70% specificity. There was heterogeneity in accuracy by country, and females and PLWH had lower sensitivity while males and people with a history of TB had lower specificity. The performance remained stable regardless of diabetes status. When country- and population-specific thresholds were applied, at least one CAD product could achieve or approach the target accuracy for each country and sub-group, except for PLWH and those with a history of TB. Conclusions: Multiple CAD algorithms can achieve or exceed the minimum target accuracy for a TB triage test, with improvement when using setting- or population-specific thresholds. Further efforts are needed to integrate CAD into routine TB case detection programs in high-burden communities. Competing Interests: CONFLICTS OF INTEREST The authors declare no conflicts of interest. The installation and use of the different CAD software evaluated in this manuscript was provided free of charge by all CAD vendors to FIND. CAD vendors did not have any role in the study design, data collection, analysis, the decision to publish or the preparation of the manuscript.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu