The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Diagnostic Accuracy of Computer-Aided Detection of Pulmonary Tuberculosis in Chest Radiographs: A Validation Study from Sub-Saharan Africa
Open accessAbstract
BACKGROUND: Chest radiography to diagnose and screen for pulmonary tuberculosis has limitations, especially due to inter-reader variability. Automating the interpretation has the potential to overcome this drawback and to deliver objective and reproducible results. The CAD4TB software is a computer-aided detection system that has shown promising preliminary findings. Evaluation studies in different settings are needed to assess diagnostic accuracy and practicability of use. METHODS: CAD4TB was evaluated on chest radiographs of patients with symptoms suggestive of pulmonary tuberculosis enrolled in two cohort studies in Tanzania. All patients were characterized by sputum smear microscopy and culture including subsequent antigen or molecular confirmation of Mycobacterium tuberculosis (M.tb) to determine the reference standard. Chest radiographs were read by the software and two human readers, one expert reader and one clinical officer. The sensitivity and specificity of CAD4TB was depicted using receiver operating characteristic (ROC) curves, the area under the curve calculated and the performance of the software compared to the results of human readers. RESULTS: Of 861 study participants, 194 (23%) were culture-positive for M.tb. The area under the ROC curve of CAD4TB for the detection of culture-positive pulmonary tuberculosis was 0.84 (95% CI 0.80-0.88). CAD4TB was significantly more accurate for the discrimination of smear-positive cases against non TB patients than for smear-negative cases (p-value<0.01). It differentiated better between TB cases and non TB patients among HIV-negative compared to HIV-positive individuals (p<0.01). CAD4TB significantly outperformed the clinical officer, but did not reach the accuracy of the expert reader (p = 0.02), for a tuberculosis specific reading threshold. CONCLUSION: CAD4TB accurately distinguished between the chest radiographs of culture-positive TB cases and controls. Further studies on cost-effectiveness, operational and ethical aspects should determine its place in diagnostic and screening algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
CAD at varied thresholds achieves higher sensitivity than human readers.
“As in other studies, we have demonstrated that CAD at varied thresholds achieves higher sensitivity than human readers [6,8,14].”
From Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey (2022) · cites this paper as [14]
Table 4 (Results; page unavailable) shows that CAD4TB reached 95% sensitivity at one cut-off, exceeding the expert reader’s highest listed sensitivity of 84%. But the clinical officer reached 97% at the ‘any abnormality’ threshold, and the Results compare CAD with readers at matched sensitivities. The paper therefore supports higher sensitivity at some thresholds, not a general advantage over human readers. (LLM, conf=0.87)
Experimental — accuracy not yet measuredThe majority of studies reporting on CAD threshold determination only included individuals who met criteria for microbiological testing.
“The majority of studies reporting on CAD threshold determination only included individuals who met some criteria for microbiological testing, such as having symptoms and/or abnormal chest radiographs [8, 16–27].”
From Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. (2024) · cites this paper as [16]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697
van Cleeff, M., Kivihya-Ndugga, L., Meme, H., Odhiambo, J., & Klatser, P. (2005) · BMC Infectious Diseases · doi:10.1186/1471-2334-5-111 · Cited by 199
Flagged first, then by citations
Research works printed but not linked: 28
- A Story, 2012, Active case finding for pulmonary tuberculosis using mobile digital chest radiography: an observational study, Int J Tuberc Lung Dis, 16, 1461, 10.5588/ijtld.11.0773 · DOI
- AH Van't Hoog, 2011, High sensitivity of chest radiograph reading by clinical officers in a tuberculosis prevalence survey, Int J Tuberc Lung Dis, 15, 1308, 10.5588/ijtld.11.0004 · DOI
- S Den Boon, 2006, An evaluation of symptom and chest radiographic screening in tuberculosis prevalence surveys, Int J Tuberc Lung Dis, 10, 876
- S Graham, 2002, Chest radiograph abnormalities associated with tuberculosis: reproducibility and yield of active cases, Int J Tuberc Lung Dis, 6, 137
- S Den Boon, 2005, Development and evaluation of a new chest radiograph reading and recording system for epidemiological surveys of tuberculosis and lung disease, Int J Tuberc Lung Dis, 9, 1088
- JP Zellweger, 2006, Intra-observer and overall agreement in the radiological assessment of tuberculosis, Int J Tuberc Lung Dis, 10, 1123
- Y Balabanova, 2005, Variability in interpretation of chest radiographs among Russian study, BMJ, 331, 379, 10.1136/bmj.331.7513.379 · DOI
- Conners R, Harlow C, Dwyer S (1982) Radiographic image analysis: past and present. Proceedings of the 6th international conference on pattern recognition. IEEE Computer Society Press. pp. 1152–1168.
- M Samulski, 2010, Using computer-aided detection in mammography as a decision support, Eur Radiol, 20, 2323, 10.1007/s00330-010-1821-8 · DOI
- P Maduskar, 2013, Detection of tuberculosis using digital chest radiography: automated reading vs. interpretation by clinical officers, Int J Tuberc Lung Dis, 17, 1613, 10.5588/ijtld.13.0325 · DOI · Paper page
- S Jaeger, 2013, Automatic screening for tuberculosis in chest radiographs: a survey, Quant Imaging Med Surg, 3, 89
- L Hogeweg, 2010, Fusion of local and global detection systems to detect tuberculosis in chest radiographs, Med Image Comput Comput Assist Interv, 13, 650
- van Ginneken B, 2011, Computer-aided diagnosis: How to Move from the Laboratory to the Clinic, Radiology, 261, 719, 10.1148/radiol.11091710 · DOI · Paper page
- DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics Sep: 837–845. · DOI · Paper page
- Wickham H (2009) ggplot2: elegant graphics for data analysis. · DOI · Paper page
- H Wickham, 2007, Reshaping Data with the reshape Package, J Stat Softw, 21, 1, 10.18637/jss.v021.i12 · DOI
- K Siddiqi, 2003, Clinical diagnosis of smear-negative pulmonary tuberculosis in low-income countries: the current evidence, Lancet Infect Dis, 3, 288, 10.1016/S1473-3099(03)00609-1 · DOI
- PB Fourie, 1980, Follow-up Tuberculosis Prevalence Survey of Transkei, Tubercle, 61, 71, 10.1016/0041-3879(80)90013-6 · DOI
- PCAM Buijtels, 2009, Nontuberculous Mycobacteria, Zambia, Emerg Infect Dis, 15, 242, 10.3201/eid1502.080006 · DOI
- G Aliyu, 2013, Prevalence of non-tuberculous mycobacterial infections among tuberculosis suspects in Nigeria, PLoS One, 8, e63170, 10.1371/journal.pone.0063170 · DOI
- Ministry of Health and Social Welfare (2006) Manual of the National Tuberculosis and Leprosy Programme in Tanzania, 5th Edition.
- Ministry of Health Uganda (2010) Manual of the National Tuberculosis and Leprosy Programme, 2nd Edition.
- Ministry of Health and Social Services Namibia (2011) National Guidelines for the Management of Tuberculosis, 3rd Edition.
- Tuberculosis Leprosy and TB/HIV Prevention and Control Programme (2008) Federal Ministry of Health Ethiopia Manual, 4th Edition.
- K Kranzer, 2013, The benefits to communities and individuals of screening for active tuberculosis disease: a systematic review, Int J Tuberc Lung Dis, 17, 432, 10.5588/ijtld.12.0743 · DOI
- M Uplekar, 2013, Programmatic approaches to screening for active tuberculosis, Int J Tuberc Lung Dis, 17, 1248, 10.5588/ijtld.13.0199 · DOI
- WHO (2013) Workshop to scale up the implementation of collaborative TB/HIV activities in Africa, 10- 11 April, 2013. Maputo, Mozambique: Meeting Report. World Health Organization. Available: http://www.who.int/hiv/pub/meetingreports/maputo_access/en/index.html. Accessed 2013 Nov 24.
- F Zennaro, 2013, Digital Radiology to Improve the Quality of Care in Countries with Limited Resources: A Feasibility Study from Angola, PLoS One, 8, e73939, 10.1371/journal.pone.0073939 · DOI
Cited by
Sorted by citations
Qin, Z. Z., Sander, M. S., Rai, B., Titahong, C. N., Sudrungrot, S., Laah, S. N., Adhikari, L. M., Carter, E. J., Puri, L., Codlin, A. J., et al. (2019) · Scientific Reports · doi:10.1038/s41598-019-51503-3 · Cited by 289
Hwang, E. J., Park, S., Jin, K.-N., Kim, J. I., Choi, S. Y., Lee, J. H., Goo, J. M., Aum, J., Yim, J.-J., Park, C. M., et al. (2019) · Clinical Infectious Diseases · doi:10.1093/cid/ciy967 · Cited by 241
Artificial Intelligence for healthcare in africa
Owoyemi, A., Owoyemi, J., Osiyemi, A., & Boyd, A. (2020) · Frontiers in Digital Health · doi:10.3389/fdgth.2020.00006 · Cited by 199
Melendez, J., Sánchez, C. I., Philipsen, R. H. H. M., Maduskar, P., Dawson, R., Theron, G., Dheda, K., & van Ginneken, B. (2016) · Scientific Reports · doi:10.1038/srep25265 · Cited by 152
Self-citationFehr, J., Konigorski, S., Olivier, S., Gunda, R., Surujdeen, A., Gareta, D., Smit, T., Baisley, K., Moodley, S., Moosa, Y., et al. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00471-y · Cited by 74
Ahmad Khan, F., Pande, T., Tessema, B., Song, R., Benedetti, A., Pai, M., Lönnroth, K., & Denkinger, C. M. (2017) · European Respiratory Journal · doi:10.1183/13993003.00953-2017 · Cited by 59
Performance of Deep Learning Model in Detecting Operable Lung Cancer With Chest Radiographs
Cha, M. J., Chung, M. J., Lee, J. H., & Lee, K. S. (2019) · Journal of Thoracic Imaging · doi:10.1097/rti.0000000000000388 · Cited by 56
Mungai, B., Ong‘angò, J., Ku, C. C., Henrion, M. Y. R., Morton, B., Joekes, E., Onyango, E., Kiplimo, R., Kirathe, D., Masini, E., et al. (2022) · PLOS Global Public Health · doi:10.1371/journal.pgph.0001272 · Cited by 24
Vanobberghen, F., Keter, A. K., Jacobs, B. K. M., Glass, T. R., Lynen, L., Law, I., Murphy, K., van Ginneken, B., Ayakaka, I., van Heerden, A., et al. (2024) · ERJ Open Research · doi:10.1183/23120541.00508-2023 · Cited by 13
“We did not observe noticeable differences in diagnostic accuracy among people living with HIV, in line with one other study [12], while others found poorer performance among people living with HIV [8, 16, 21, 22].”
BackgroundResultSelf-citation
Metadata
- Authors
- Breuninger, M., van Ginneken, B., Philipsen, R. H. H. M., Mhimbira, F., Hella, J. J., Lwilla, F., van den Hombergh, J., Ross, A., Jugheli, L., Wagner, D., & Reither, K.
- Affiliations
- Ifakara Health Institute (TZ)
- Radboud University Medical Center (NL)
- Swiss Tropical and Public Health Institute (CH)
- University Medical Center Freiburg (DE)
- Corresponding author
- Breuninger, Marianne
- ORCID
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2014-09-05
- Volume
- 9
- Issue
- 9
- Pages
- e106381
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC4156349
- OpenAlex
- W2046297223
- Cited by
- 101
- References
- 2
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 12 · 2023: 6 · 2022: 14 · 2021: 12 · 2020: 6 · 2019: 8 · 2018: 9 · 2017: 10 · 2016: 6 · 2015: 7
- FWCI
- 5.39
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- edoc (University of Basel) (acceptedVersion)
- IHI Repository (acceptedVersion)
- Radboud Repository (Radboud University) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Radboud Repository (Radboud University) (submittedVersion)
- edoc (University of Basel)
- Funders
- European and Developing Countries Clinical Trials Partnership
- Topics
- Health Sciences › Medicine › Infectious Diseases › Tuberculosis Research and Epidemiology
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- pulmonary tuberculosis, computer-aided detection, CAD4TB, chest radiograph, diagnostic accuracy, Mycobacterium tuberculosis, tuberculosis screening, inter-reader variability, HIV coinfection, Tanzania, sub-Saharan Africa
- MeSH terms
- Adult, Female, HIV Seropositivity, Humans, Male, Middle Aged, Risk Factors, ROC Curve, Sensitivity and Specificity, Radiography, Thoracic, Tomography, X-Ray Computed, Tuberculosis, Pulmonary, Reproducibility of Results, Africa South of the Sahara, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
