Tavaziva, Gamuchirai, Harris, Miriam ORCID: 0000-0003-3870-4858, Abidi, Syed K., Geric, Coralie, Breuninger, Marianne, Dheda, Keertan, Esmail, Aliasgar, Muyoyeta, Monde, Reither, Klaus, Majidulla, Arman, Khan, Aamir J., Campbell, Jonathon R., David, Pierre-Marie, Denkinger, Claudia, Miller, Cecily, Nathavitharana, Ruvandhi, Pai, Madhukar, Benedetti, Andrea and Khan, Faiz Ahmad . Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy. Clin. Infect. Dis.. CARY: OXFORD UNIV PRESS INC. ISSN 1537-6591

Full text not available from this repository.

Abstract

Background Automated radiologic analysis using computer-aided detection software (CAD) could facilitate chest X-ray (CXR) use in tuberculosis diagnosis. There is little to no evidence on the accuracy of commercially available deep learning-based CAD in different populations, including patients with smear-negative tuberculosis and people living with human immunodeficiency virus (HIV, PLWH). Methods We collected CXRs and individual patient data (IPD) from studies evaluating CAD in patients self-referring for tuberculosis symptoms with culture or nucleic acid amplification testing as the reference. We reanalyzed CXRs with three CAD programs (CAD4TB version (v) 6, Lunit v3.1.0.0, and qXR v2). We estimated sensitivity and specificity within each study and pooled using IPD meta-analysis. We used multivariable meta-regression to identify characteristics modifying accuracy. Results We included CXRs and IPD of 3727/3967 participants from 4/7 eligible studies. 17% (621/3727) were PLWH. 17% (645/3727) had microbiologically confirmed tuberculosis. Despite using the same threshold score for classifying CXR in every study, sensitivity and specificity varied from study to study. The software had similar unadjusted accuracy (at 90% pooled sensitivity, pooled specificities were: CAD4TBv6, 56.9% [95% confidence interval {CI}: 51.7-61.9]; Lunit, 54.1% [95% CI: 44.6-63.3]; qXRv2, 60.5% [95% CI: 51.7-68.6]). Adjusted absolute differences in pooled sensitivity between PLWH and HIV-uninfected participants were: CAD4TBv6, -13.4% [-21.1, -6.9]; Lunit, +2.2% [-3.6, +6.3]; qXRv2: -13.4% [-21.5, -6.6]; between smear-negative and smear-positive tuberculosis was: were CAD4TBv6, -12.3% [-19.5, -6.1]; Lunit, -17.2% [-24.6, -10.5]; qXRv2, -16.6% [-24.4, -9.9]. Accuracy was similar to human readers. Conclusions For CAD CXR analysis to be implemented as a high-sensitivity tuberculosis rule-out test, users will need threshold scores identified from their own patient populations and stratified by HIV and smear status. An individual patient data (IPD) meta-analysis found the accuracy of commercially available deep learning-based chest X-ray analysis software for detecting tuberculosis varied between studies and by patient characteristics. Diagnostic heterogeneity poses an implementation challenge for this novel technology.

Item Type: Journal Article
Creators:
CreatorsEmailORCIDORCID Put Code
Tavaziva, GamuchiraiUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Harris, MiriamUNSPECIFIEDorcid.org/0000-0003-3870-4858UNSPECIFIED
Abidi, Syed K.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Geric, CoralieUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Breuninger, MarianneUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Dheda, KeertanUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Esmail, AliasgarUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Muyoyeta, MondeUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Reither, KlausUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Majidulla, ArmanUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Khan, Aamir J.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Campbell, Jonathon R.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
David, Pierre-MarieUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Denkinger, ClaudiaUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Miller, CecilyUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Nathavitharana, RuvandhiUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Pai, MadhukarUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Benedetti, AndreaUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Khan, Faiz AhmadUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
URN: urn:nbn:de:hbz:38-603505
DOI: 10.1093/cid/ciab639
Journal or Publication Title: Clin. Infect. Dis.
Publisher: OXFORD UNIV PRESS INC
Place of Publication: CARY
ISSN: 1537-6591
Language: English
Faculty: Unspecified
Divisions: Unspecified
Subjects: no entry
Uncontrolled Keywords:
KeywordsLanguage
RADIOGRAPHSMultiple languages
Immunology; Infectious Diseases; MicrobiologyMultiple languages
URI: http://kups.ub.uni-koeln.de/id/eprint/60350

Downloads

Downloads per month over past year

Altmetric

Export

Actions (login required)

View Item View Item