The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists
Open accessAbstract
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.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Figures



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?
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
Research works printed but not linked: 1
- E Potchen, 1979, Effect of clinical history data on chest film interpretation-direction or distraction, Invest Radiol, 14, 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. https://app.cochat.ai/papers/10.1371/journal.pmed.1002686
- The paper
- 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., . . . Lungren, M. P. (2018). Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLOS Medicine. https://doi.org/10.1371/journal.pmed.1002686
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.