The Case for User-Centered Artificial Intelligence in Radiology
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Past technology transition successes and failures have demonstrated the importance of user-centered design and the science of human factors; these approaches will be critical to the success of artificial intelligence in radiology.
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
Current Applications and Future Impact of Machine Learning in Radiology
Choy, G., Khalilzadeh, O., Michalski, M., Do, S., Samir, A. E., Pianykh, O. S., Geis, J. R., Pandharipande, P. V., Brink, J. A., & Dreyer, K. J. (2018) · Radiology · doi:10.1148/radiol.2018171820 · Cited by 800 · cited 1×
“A newer deep learning methods, have shown great promise in radiology research and in translation to practice (1).”
Electronic Health Record Usability Issues and Potential Contribution to Patient Harm
Howe, J. L., Adams, K. T., Hettinger, A. Z., & Ratwani, R. M. (2018) · JAMA · doi:10.1001/jama.2018.1171 · Cited by 281 · cited 2×
“Finding relevant patient information in the EHR can be challenging to navigate, and components such as clinical decision support that should enhance clinical decision making can lead to greater confusion (6).”
BackgroundSelf-citationMachine Learning in Radiology: Applications Beyond Image Interpretation
Lakhani, P., Prater, A. B., Hutson, R. K., Andriole, K. P., Dreyer, K. J., Morey, J., Prevedello, L. M., Clark, T. J., Geis, J. R., Itri, J. N., et al. (2018) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2017.09.044 · Cited by 250 · cited 1×
“One must also consider that the radiologist or interpretive use cases may be the minority of potential use cases in radiology (13).”
BackgroundRatwani, R. M., Fairbanks, R. J., Hettinger, A. Z., & Benda, N. C. (2015) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv050 · Cited by 204 · cited 2×
“One reason EHR usability may be challenging is due to the failure to properly employ UCD to focus on understanding clinician cognitive processes and their unique workflows (2).”
BackgroundMethodSelf-citationIdentifying electronic health record usability and safety challenges in pediatric settings
Ratwani, R. M., Savage, E., Will, A., Fong, A., Karavite, D., Muthu, N., Rivera, A. J., Gibson, C., Asmonga, D., Moscovitch, B., et al. (2018) · Health Affairs · doi:10.1377/hlthaff.2018.0699 · Cited by 163 · cited 1×
“Suboptimal EHR usability has led to increased clinician frustration and burden, as well as patient safety consequences, and highlights key parallels that we must focus on as radiology undergoes its own AI technology transition (5,6).”
BackgroundSelf-citationImproving the radiologist-CAD interaction: designing for appropriate trust
Jorritsma, W., Cnossen, F., & van Ooijen, P. M. A. (2015) · Clinical Radiology · doi:10.1016/j.crad.2014.09.017 · Cited by 61 · cited 1×
“The lack of UCD in prior generations of AI, namely computer-aided detection (CAD) in mammography, has been a major contributor to poorer-than-expected augmented clinical performance based on performance of radiologists and CAD alone, likely related to lack of trust (4).”
BackgroundThe Impact of Interruptions on Chest Radiograph Interpretation
Wynn, R. M., Howe, J. L., Kelahan, L. C., Fong, A., Filice, R. W., & Ratwani, R. M. (2018) · Academic Radiology · doi:10.1016/j.acra.2018.03.016 · Cited by 35 · cited 2×
“Other cognitive demands that may be placed on the user, such as output from other AI models, interruptions from clinicians or phone calls, and potential critical findings and communication requirements, should be considered (12).”
BackgroundSelf-citationMigrating to the Modern PACS: Challenges and Opportunities
Berkowitz, S. J., Wei, J. L., & Halabi, S. S. (2018) · Radiographics · doi:10.1148/rg.2018180161 · Cited by 30 · cited 1×
“In the design phase of any radiology application, it is optimal to have the radiologist or relevant health care provider involved early and continuously (11) to ensure that the application will meet their needs and aid clinical care in an effective way.”
BackgroundGoldstein, M. M., & Thorpe, J. H. (2010) · PubMed · Cited by 21
Research works printed but not linked: 4
- International Organization for Standardization, 2010, ISO 9241-210:2010: ergonomics of human-system interaction—part 210: human centred design for interactive systems
- Wickens CD, 2013, Engineering psychology & human performance
- User Centered Design Process, Varian Medical Systems/The Drummond Group
- User Centered design improves workflows in radiology – A look at Healthcare IT Development at Siemens; Hospital and Healthcare Management
Cited by
Enhancing trust in AI through industry self-governance.
Roski, J., Maier, E. J., Vigilante, K., Kane, E. A., & Matheny, M. E. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocab065 · Cited by 83
Pahud de Mortanges, A., Luo, H., Shu, S. Z., Kamath, A., Suter, Y., Shelan, M., Pöllinger, A., & Reyes, M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01190-w · Cited by 93
Lekadir, K., Osuala, R., Gallin, C., Lazrak, N., Kushibar, K., Tsakou, G., Aussó, S., Alberich, L. C., Marias, K., Tsiknakis, M., et al. (2021) · arXiv · doi:10.48550/arxiv.2109.09658 · Cited by 58
Evaluating Artificial Intelligence Systems to Guide Purchasing Decisions
Filice, R. W., Mongan, J., & Kohli, M. D. (2020) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2020.09.045 · Cited by 27
Self-citationEvaluation and Regulation of Artificial Intelligence Medical Devices for Clinical Decision Support
Weissman, G. E. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095824 · Cited by 37
Metadata
- Authors
- Filice, R. W., & Ratwani, R. M.
- Affiliations
- MedStar Georgetown University Hospital (US)
- Venue
- Radiology: Artificial Intelligence
- Published
- 2020-05-01
- Volume
- 2
- Issue
- 3
- Pages
- e190095
- ISSN
- 2638-6100 (ISSN-L)
- PMC
- PMC8082296
- OpenAlex
- W3025950232
- Semantic Scholar
- f9ae43c0e4ffed27be4c442a04b5c25ce2d1da9c
- Cited by
- 30
- References
- 9
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 6 · 2023: 5 · 2022: 1 · 2021: 5 · 2020: 2
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Radiology Artificial Intelligence (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiology practices and education
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- user-centered design, human factors, artificial intelligence in radiology, technology adoption, radiology workflow, human-AI interaction
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: The Case for User-Centered Artificial Intelligence in Radiology. https://app.cochat.ai/papers/10.1148/ryai.2020190095
- The paper
- Filice, R. W., & Ratwani, R. M. (2020). The Case for User-Centered Artificial Intelligence in Radiology. Radiology: Artificial Intelligence. https://doi.org/10.1148/ryai.2020190095
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.