Evidence map›Paper›PMID 31628424›Full record

ArticleScientific reports2019

Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems.

Zhi Zhen Qin, Melissa S Sander, Bishwa Rai, Collins N Titahong, Santat Sudrungrot, Sylvain N Laah, Lal Mani Adhikari, E Jane Carter, Lekha Puri, Andrew J Codlin and 1 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Scientific reports, 2019. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 149 papers, 6 of them syntheses that pooled it.

0numbers the graph read from it
0cells of the map it votes in
149citing papers in PubMed, 6 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

149 citing papers in PubMed, 6 syntheses or guidelines pooled it.

  1. Pooled it
  2. Pooled it
  3. Pooled it
  4. Pooled it
  5. Pooled it
  6. Screening tests for active pulmonary tuberculosis in children.The Cochrane database of systematic reviews · 2021
    Pooled it
  7. Trial
  8. Trial
  9. Article
  10. Article
  11. Article
  12. Article
  13. Review
  14. Article
  15. Article
  16. Article
  17. Review
  18. Article
  19. Review
  20. Article

89 more citing papers are in PubMed but not listed here.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

Zhi Zhen QinStop TB Partnership, Chemin du Pommier 40, 1218 Le Grand-Saconnex, Geneva, Switzerland.ORCID http://orcid.org/0000-0002-3956-5223
Melissa S SanderTuberculosis Reference Laboratory Bamenda, PO Box 586, Bamenda, Cameroon.
Bishwa RaiInternational Organization for Migration, Migration Health Department, Kathmandu, Nepal.
Collins N TitahongTuberculosis Reference Laboratory Bamenda, PO Box 586, Bamenda, Cameroon.
Santat SudrungrotInternational Organization for Migration, Migration Health Department, Kathmandu, Nepal.
Sylvain N LaahTuberculosis Reference Laboratory Bamenda, PO Box 586, Bamenda, Cameroon.
Lal Mani AdhikariInternational Organization for Migration, Migration Health Department, Kathmandu, Nepal.
E Jane CarterDepartment of Medicine, Division of Pulmonary, Critical Care and Sleep, Warren Alpert Medical School, Brown University, Rhode Island, USA.
Lekha PuriStop TB Partnership, Chemin du Pommier 40, 1218 Le Grand-Saconnex, Geneva, Switzerland.
Andrew J CodlinStop TB Partnership, Chemin du Pommier 40, 1218 Le Grand-Saconnex, Geneva, Switzerland.
Jacob CreswellStop TB Partnership, Chemin du Pommier 40, 1218 Le Grand-Saconnex, Geneva, Switzerland. jacobc@stoptb.org.ORCID http://orcid.org/0000-0002-4885-940X

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR read by two groups of radiologists and the DL systems. Xpert was used as the reference standard. The area under the curve of the three systems was similar: Lunit (0.94, 95% CI: 0.93-0.96), qXR (0.94, 95% CI: 0.92-0.97) and CAD4TB (0.92, 95% CI: 0.90-0.95). When matching the sensitivity of the radiologists, the specificities of the DL systems were significantly higher except for one. Using DL systems to read CXRs could reduce the number of Xpert MTB/RIF tests needed by 66% while maintaining sensitivity at 95% or better. Using a universal cutoff score resulted different performance in each site, highlighting the need to select scores based on the population screened. These DL systems should be considered by TB programs where human resources are constrained, and automated technology is available.

Indexed as

Data AccuracyDeep LearningAdultArea Under CurveCameroonDNA, BacterialFemaleHumansMaleMass ScreeningMiddle AgedMycobacterium tuberculosisNepalNucleic Acid Amplification TechniquesRadiography, ThoracicRetrospective StudiesDNA, Bacterial

Identifiers

PMID31628424
PMCPMC6802077

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.