Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Artificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational “stress tests”. Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5–22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.
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
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
The REDCap consortium: building an international community of software platform partners
Harris, P. A., Taylor, R., Minor, B. L., Elliott, V., Fernandez, M., O'Neal, L., McLeod, L., Delacqua, G., Delacqua, F., Kirby, J., et al. (2019) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103208 · Cited by 24,013
Assessing the Performance of Prediction Models: A Framework for Traditional and Novel Measures
Steyerberg, E. W., Vickers, A. J., Cook, N. R., Gerds, T., Gonen, M., Obuchowski, N., Pencina, M. J., & Kattan, M. W. (2010) · Epidemiology · doi:10.1097/ede.0b013e3181c30fb2 · Cited by 5,170
Tschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., et al. (2018) · 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) · doi:10.1109/isbi.2018.8363547 · Cited by 2,620
Self-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01501 · Cited by 1,090
PH2 - A dermoscopic image database for research and benchmarking
Mendonca, T., Ferreira, P. M., Marques, J. S., Marcal, A. R. S., & Rozeira, J. (2013) · 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2013.6610779 · Cited by 1,009 · cited 4×
“Test datasets were from the VAMC, the University of California, San Francisco (UCSF), Hospital Pedro Hispano (PH2) 12 , and the dermoscopic and non-dermoscopic Melanoma Classi fi cation Benchmarks (MClass-D, and MClass-ND, respectively) 13 .”
BackgroundMethodInfluentialA deep learning system for differential diagnosis of skin diseases
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0842-3 · Cited by 853
Cited by
Long, G. V., Swetter, S. M., Menzies, A. M., Gershenwald, J. E., & Scolyer, R. A. (2023) · The Lancet · doi:10.1016/s0140-6736(23)00821-8 · Cited by 746
Covasim: An agent-based model of COVID-19 dynamics and interventions
Kerr, C. C., Stuart, R. M., Mistry, D., Abeysuriya, R. G., Rosenfeld, K., Hart, G. R., Núñez, R. C., Cohen, J. A., Selvaraj, P., Hagedorn, B., et al. (2021) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1009149 · Cited by 685
Young, A. T., Amara, D., Bhattacharya, A., & Wei, M. L. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00132-1 · Cited by 400
Self-citationManyazewal, T., Woldeamanuel, Y., Blumberg, H. M., Fekadu, A., & Marconi, V. C. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00487-4 · Cited by 177
Eche, T., Schwartz, L. H., Mokrane, F.-Z., & Dercle, L. (2021) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2021210097 · Cited by 163
Metadata
- Authors
- Young, A. T., Fernandez, K., Pfau, J., Reddy, R., Cao, N. A., von Franque, M. Y., Johal, A., Wu, B. V., Wu, R. R., Chen, J. Y., Fadadu, R. P., Vasquez, J. A., Tam, A., Keiser, M. J., & Wei, M. L.
- Venue
- npj Digital Medicine
- Published
- 2021-01-21
- Volume
- 4
- Issue
- 1
- Pages
- 10-10
- ISSN
- 2398-6352 (ISSN-L)
- OpenAlex
- W3121506861
- Cited by
- 51
- References
- 17
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- gold
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: Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models. https://app.cochat.ai/papers/10.1038/s41746-020-00380-6
- The paper
- Young, A. T., Fernandez, K., Pfau, J., Reddy, R., Cao, N. A., von Franque, M. Y., Johal, A., Wu, B. V., Wu, R. R., Chen, J. Y., Fadadu, R. P., Vasquez, J. A., Tam, A., Keiser, M. J., & Wei, M. L. (2021). Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models. npj Digital Medicine. https://doi.org/10.1038/s41746-020-00380-6
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.