Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. METHODS AND FINDINGS: We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. CONCLUSIONS: In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Many AI models developed for radiology tasks have shown excellent performance equal to or even surpassing human experts (e.g.3,4)”
From Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays (2023) · cites this paper as [3]
The cited source says what the claim attributes to it.
In the citing paper
“deep learning models have demonstrated diagnostic accuracy comparable to that of human experts in narrow clinical tasks for several medical domains and imaging modalities, including chest and extremity X-rays8–10, computed tomography (CT)11, magnetic resonance imaging (MRI)12, whole slide images (WSI)13,14, and dermatology images15.”
From Self-supervised learning for medical image classification: a systematic review and implementation guidelines (2023) · cites this paper as [9]
The cited source says what the claim attributes to it.
In the citing paper
“While several studies have compared clinician performance with machine learning (ML) models in other fields-such as dermatology [26,27], radiology [28] and pathology [29]-”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [28]
The cited source says what the claim attributes to it.
In the citing paper
“Previous Head-to-Head comparisons of clinician and AI performance-such as in dermatology [26,27], radiology [28], and pathology [29]-have provided valuable insights, but they remained confined to image-based or narrowly defined diagnostic tasks.”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [28]
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
A Coefficient of Agreement for Nominal Scales
Cohen, J. (1960) · Educational and Psychological Measurement · doi:10.1177/001316446002000104 · Cited by 42,398
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
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
Zhang, Q., Wang, C., Zheng, M., Li, Y., Li, J., Zhang, L., Shang, X., & Yan, C. (2015) · Cerebrovascular Diseases · doi:10.1159/000369778 · Cited by 11,533
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Projections of Global Mortality and Burden of Disease from 2002 to 2030
Mathers, C. D., & Loncar, D. (2006) · PLoS Medicine · doi:10.1371/journal.pmed.0030442 · Cited by 11,386
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293
Lakhani, P., & Sundaram, B. (2017) · Radiology · doi:10.1148/radiol.2017162326 · Cited by 1,775
Setio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., Wille, M. M. W., Naqibullah, M., Sanchez, C. I., & van Ginneken, B. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2536809 · Cited by 1,258
irr: Various Coefficients of Interrater Reliability and Agreement
Matthias Gamer <m.gamer@uke.uni-hamburg.de>, J. L. <. C. A. (2005) · CRAN: Contributed Packages · doi:10.32614/cran.package.irr · Cited by 540
Chest pathology detection using deep learning with non-medical training
Bar, Y., Diamant, I., Wolf, L., Lieberman, S., Konen, E., & Greenspan, H. (2015) · 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2015.7163871 · Cited by 392
gridExtra: Miscellaneous Functions for "Grid" Graphics
Auguie, B. (2010) · CRAN: Contributed Packages · doi:10.32614/cran.package.gridextra · Cited by 389
Cicero, M., Bilbily, A., Colak, E., Dowdell, T., Gray, B., Perampaladas, K., & Barfett, J. (2017) · Investigative Radiology · doi:10.1097/rli.0000000000000341 · Cited by 247
Guan, Q., Huang, Y., Zhong, Z., Zheng, Z., Zheng, L., & Yang, Y. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09927 · Cited by 226
Interpretation of Plain Chest Roentgenogram
Raoof, S., Feigin, D., Sung, A., Raoof, S., Irugulpati, L., & Rosenow, E. C. (2012) · Chest · doi:10.1378/chest.10-1302 · Cited by 218
Estimation of the Means of Dependent Variables
Dunn, O. J. (1958) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177706443 · Cited by 211
Radiologist shortage leaves patient care at risk, warns royal college
Rimmer, A. (2017) · BMJ · doi:10.1136/bmj.j4683 · Cited by 193
Learning to diagnose from scratch by exploiting dependencies among labels
Li, Y., Poblenz, E., Dagunts, D., Covington, B., Bernard, D., & Lyman, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10501 · Cited by 181
Goddard, P., Leslie, A., Jones, A., Wakeley, C., & Kabala, J. (2001) · The British Journal of Radiology · doi:10.1259/bjr.74.886.740949 · Cited by 134
Detection or decision errors? Missed lung cancer from the posteroanterior chest radiograph
Manning, D. J., Ethell, S. C., & Donovan, T. (2004) · The British Journal of Radiology · doi:10.1259/bjr/28883951 · Cited by 132
Learning to detect chest radiographs containing pulmonary lesions using visual attention networks
Pesce, E., Joseph Withey, S., Ypsilantis, P.-P., Bakewell, R., Goh, V., & Montana, G. (2019) · Medical Image Analysis · doi:10.1016/j.media.2018.12.007 · Cited by 126
Looking for Cancer: Expertise Related Differences in Searching and Decision Making
Donovan, T., & Litchfield, D. (2013) · Applied Cognitive Psychology · doi:10.1002/acp.2869 · Cited by 99
Computer-Displayed Eye Position as a Visual Aid to Pulmonary Nodule Interpretation
Kundel, H. L., Nodine, C. F., & Krupinski, E. A. (1990) · Investigative Radiology · doi:10.1097/00004424-199008000-00004 · Cited by 96
An Analysis of Perceptual and Cognitive Factors in Radiographic Interpretation
Carmody, D. P., Nodine, C. F., & Kundel, H. L. (1980) · Perception · doi:10.1068/p090339 · Cited by 86
Schalekamp, S., van Ginneken, B., Koedam, E., Snoeren, M. M., Tiehuis, A. M., Wittenberg, R., Karssemeijer, N., & Schaefer-Prokop, C. M. (2014) · Radiology · doi:10.1148/radiol.14131315 · Cited by 80
Maduskar, P., Muyoyeta, M., Ayles, H., Hogeweg, L., Peters-Bax, L., & van Ginneken, B. (2013) · The International Journal of Tuberculosis and Lung Disease · doi:10.5588/ijtld.13.0325 · Cited by 77
Laifer, G., Widmer, A. F., Simcock, M., Bassetti, S., Trampuž, A., Frei, R., Tamm, M., Battegay, M., & Flückiger, U. M. (2007) · The American Journal of Medicine · doi:10.1016/j.amjmed.2006.10.025 · Cited by 58
MESS: Miscellaneous Esoteric Statistical Scripts
Ekstrøm, C. T. (2012) · CRAN: Contributed Packages · doi:10.32614/cran.package.mess · Cited by 58
Gopal, M., Abdullah, S. E., Grady, J. J., & Goodwin, J. S. (2010) · Journal of Thoracic Oncology · doi:10.1097/jto.0b013e3181e0b977 · Cited by 56
Clinical Characteristics and Prognosis of Incidentally Detected Lung Cancers
Quadrelli, S., Lyons, G., Colt, H., Chimondeguy, D., & Buero, A. (2015) · International Journal of Surgical Oncology · doi:10.1155/2015/287604 · Cited by 47
Welling, R. D., Azene, E., Kalia, V., Pongpirul, K., Nordvig, A. S., Sydnor, R. H., Lungren, M. P., Johnson, B. E., Kimble, C., Wiktorek, S., et al. (2011) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2011.01.011 · Cited by 43
Self-citationVisual Skill Correlation with Detection of Solitary Pulmonary Nodules
Bass, J. C., & Chiles, C. (1990) · Investigative Radiology · doi:10.1097/00004424-199009000-00006 · Cited by 33
Bastawrous, S., & Carney, B. W. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-016-9937-2 · Cited by 31
Novak, R. D., Novak, N. J., Gilkeson, R., Mansoori, B., & Aandal, G. (2013) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-012-9565-4 · Cited by 26
Mor, Z., Leventhal, A., Weiler‐Ravell, D., Peled, N., & Lerman, Y. (2012) · Respiratory Care · doi:10.4187/respcare.01475 · Cited by 26
The Effect of Comparison Films Upon Resident Interpretation of Pediatric Chest Radiographs
Berbaum, K. S., Franken, E. A., & Smith, W. L. (1985) · Investigative Radiology · doi:10.1097/00004424-198503000-00004 · Cited by 22
Meziane, M. A., Mazzone, P. J., Novak, E. L., Lieber, M. L., Lababede, O., Phillips, M., & Obuchowski, N. A. (2010) · Journal of Thoracic Imaging · doi:10.1097/rti.0b013e3181f240bc · Cited by 22
Active and passive screening for tuberculosis in Vaud Canton, Switzerland
Monney, M. (2005) · Swiss Medical Weekly · doi:10.4414/smw.2005.10933 · Cited by 19
Computer-aided Detection Fidelity of Pulmonary Nodules in Chest Radiograph
Dellios, N., Teichgraeber, U., Chelaru, R., Malich, A., & Papageorgiou, I. E. (2017) · Journal of Clinical Imaging Science · doi:10.4103/jcis.jcis_75_16 · Cited by 18
Mor, Z., Weinstein, O., Tischler-Aurkin, D., Leventhal, A., Alon, Y., & Grotto, I. (2015) · PubMed · Cited by 13
Learning to detect chest radiographs containing lung nodules using visual attention networksPreprint
Pesce, E., Ypsilantis, P.-P., Withey, S. J., Bakewell, R. J., Goh, V., & Montana, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.00996 · Cited by 10
Gopal, M., Abdullah, S. E., Grady, J. J., & Goodwin, J. S. (2010) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/ajrccm-conference.2010.181.1_meetingabstracts.a4406 · Cited by 5
ConSpline: Partial Linear Least-Squares Regression using Constrained Splines
Meyer, M. C. (2015) · doi:10.32614/cran.package.conspline · Cited by 1
Research works printed but not linked: 2
- Wickham H. ggplot2: Elegant Graphics for Data Analysis [Internet]. Springer-Verlag New York; 2009 Available from: http://ggplot2.org. [cited 2018 Feb 22].
- Potchen E, Gard J, Lazar P, Lahaie P, Andary M. Effect of clinical history data on chest film interpretation-direction or distraction. Invest Radiol. 1979; 14: 404– 404.
Cited by
Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2022) · Nature Medicine · doi:10.1038/s41591-021-01614-0 · Cited by 3,212
Self-citationCan AI help in screening viral and COVID-19 pneumonia?
Chowdhury, M. E. H., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M. A., Mahbub, Z. B., Islam, K. R., Khan, M. S., Iqbal, A., Emadi, N. A., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3010287 · Cited by 1,913
Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., Mahendiran, T., Moraes, G., Shamdas, M., Kern, C., et al. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30123-2 · Cited by 1,883
Big data and machine learning algorithms for health-care delivery
Ngiam, K. Y., & Khor, I. W. (2019) · The Lancet Oncology · doi:10.1016/s1470-2045(19)30149-4 · Cited by 1,424
Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J., Denniston, A. K., The SPIRIT-AI and CONSORT-AI Working Group, SPIRIT-AI and CONSORT-AI Steering Group, Chan, A.-W., Darzi, A., Holmes, C., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-1034-x · Cited by 1,421
Metadata
- Authors
- Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C. P., Patel, B. N., Yeom, K. W., Shpanskaya, K., Blankenberg, F. G., Seekins, J., Amrhein, T. J., Mong, D. A., Halabi, S. S., Zucker, E. J., Ng, A. Y., & Lungren, M. P.
- Affiliations
- Stanford University (US)
- Stanford Medicine (US)
- Duke University (US)
- University of Colorado Denver (US)
- Corresponding author
- Rajpurkar, Pranav
- ORCID
- Venue
- PLOS Medicine
- Publisher
- Public Library of Science (PLoS)
- Published
- 2018-11-20
- Volume
- 15
- Issue
- 11
- Pages
- e1002686
- ISSN
- 1549-1277 (ISSN-L)
- 1549-1676
- PMC
- PMC6245676
- OpenAlex
- W2901954625
- Cited by
- 1,449
- References
- 48
- Citations by year
- 2026: 181 · 2025: 214 · 2024: 195 · 2023: 166 · 2022: 203 · 2021: 218 · 2020: 192 · 2019: 77 · 2018: 2
- FWCI
- 84.46
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS Medicine (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Funders
- Stanford Bio-X
- National Institute of Biomedical Imaging and Bioengineering (R01EB000898)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- chest X-ray interpretation, convolutional neural networks, radiologist performance comparison, pneumonia, pleural effusion, pulmonary nodules, cardiomegaly, emphysema, hiatal hernia, tuberculosis, lung cancer, diagnostic accuracy, radiology workforce shortage, clinical implementation of AI, radiology residents
- MeSH terms
- Radiologists, Deep Learning, Clinical Competence, Diagnosis, Computer-Assisted, Humans, Pneumonia, Predictive Value of Tests, Radiographic Image Interpretation, Computer-Assisted, Retrospective Studies, Radiography, Thoracic, Reproducibility of Results
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.