Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine Fractures
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
BACKGROUND AND PURPOSE: Artificial intelligence decision support systems are a rapidly growing class of tools to help manage ever-increasing imaging volumes. The aim of this study was to evaluate the performance of an artificial intelligence decision support system, Aidoc, for the detection of cervical spinal fractures on noncontrast cervical spine CT scans and to conduct a failure mode analysis to identify areas of poor performance. MATERIALS AND METHODS: This retrospective study included 1904 emergent noncontrast cervical spine CT scans of adult patients (60 [SD, 22] years, 50.3% men). The presence of cervical spinal fracture was determined by Aidoc and an attending neuroradiologist; discrepancies were independently adjudicated. Algorithm performance was assessed by calculation of the diagnostic accuracy, and a failure mode analysis was performed. RESULTS: Aidoc and the neuroradiologist's interpretation were concordant in 91.5% of cases. Aidoc correctly identified 67 of 122 fractures (54.9%) with 106 false-positive flagged studies. Diagnostic performance was calculated as the following: sensitivity, 54.9% (95% CI, 45.7%-63.9%); specificity, 94.1% (95% CI, 92.9%-95.1%); positive predictive value, 38.7% (95% CI, 33.1%-44.7%); and negative predictive value, 96.8% (95% CI, 96.2%-97.4%). Worsened performance was observed in the detection of chronic fractures; differences in diagnostic performance were not altered by study indication or patient characteristics. CONCLUSIONS: We observed poor diagnostic accuracy of an artificial intelligence decision support system for the detection of cervical spine fractures. Many similar algorithms have also received little or no external validation, and this study raises concerns about their generalizability, utility, and rapid pace of deployment. Further rigorous evaluations are needed to understand the weaknesses of these tools before widespread implementation.
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
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719 · cited 2×
“16-18 Thus, rigorous studies to guide AI DSS installations in varied clinical settings and a greater understanding of the generalizability (or lack thereof) of AI DSSs are needed to safely translate this important tool into widespread clinical practice.”
BackgroundBenjamens, S., Dhunnoo, P., & Meskó, B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00324-0 · Cited by 1,215 · cited 2×
“findings.(12,13) These DSSs identify and subsequently flag studies with actionable results, allowing radiologists to prioritize them over scans with likely negative findings to speed the reporting of”
BackgroundPark, S. H., & Han, K. (2018) · Radiology · doi:10.1148/radiol.2017171920 · Cited by 894 · cited 1×
“AI algorithms are known to have numerous limitations, including the need for large, diverse, and unbiased datasets, 14 which can be difficult to acquire or curate 15 and operate in a manner that precludes direct interrogation of the decision process itself.”
BackgroundMcDonald, R. J., Schwartz, K. M., Eckel, L. J., Diehn, F. E., Hunt, C. H., Bartholmai, B. J., Erickson, B. J., & Kallmes, D. F. (2015) · Academic Radiology · doi:10.1016/j.acra.2015.05.007 · Cited by 460
Kim, D. W., Jang, H. Y., Kim, K. W., Shin, Y., & Park, S. H. (2019) · Korean Journal of Radiology · doi:10.3348/kjr.2019.0025 · Cited by 459 · cited 2×
“16-18 Thus, rigorous studies to guide AI DSS installations in varied clinical settings and a greater understanding of the generalizability (or lack thereof) of AI DSSs are needed to safely translate this important tool into widespread clinical practice.”
Background
Cited by
The current and future state of AI interpretation of medical images
Rajpurkar, P., & Lungren, M. P. (2023) · New England Journal of Medicine · doi:10.1056/nejmra2301725 · Cited by 443
Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis
Park, S. H., Han, K., Jang, H. Y., Park, J. E., Lee, J.-G., Kim, D. W., & Choi, J. (2023) · Radiology · doi:10.1148/radiol.220182 · Cited by 163
FDA Review of Radiologic AI Algorithms: Process and Challenges
Zhang, K., Khosravi, B., Vahdati, S., & Erickson, B. J. (2024) · Radiology · doi:10.1148/radiol.230242 · Cited by 46
Agrawal, A., Khatri, G. D., Khurana, B., Sodickson, A. D., Liang, Y., & Dreizin, D. (2023) · Emergency Radiology · doi:10.1007/s10140-023-02121-0 · Cited by 41
Sarantopoulos, A., Mastori Kourmpani, C., Yokarasa, A. L., Makamanzi, C., Antoniou, P., Spernovasilis, N., & Tsioutis, C. (2024) · Tropical Medicine and Infectious Disease · doi:10.3390/tropicalmed9100228 · Cited by 40
Metadata
- Authors
- Voter, A. F., Larson, M. E., Garrett, J. W., & Yu, J.-P. J.
- Venue
- American Journal of Neuroradiology
- Published
- 2021-06-11
- Volume
- 42
- Issue
- 8
- Pages
- 1550-1556
- ISSN
- 0195-6108 (ISSN-L)
- 1936-959X
- OpenAlex
- W3172718437
- Cited by
- 100
- References
- 5
- FWCI
- 4.06
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine Fractures. https://app.cochat.ai/papers/10.3174/ajnr.a7179
- The paper
- Voter, A. F., Larson, M. E., Garrett, J. W., & Yu, J.-P. J. (2021). Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine Fractures. American Journal of Neuroradiology. https://doi.org/10.3174/ajnr.a7179
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.