The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
Sources of bias in artificial intelligence that perpetuate healthcare disparities—A global review
Open accessAbstract
Background: While artificial intelligence (AI) offers possibilities of advanced clinical prediction and decision-making in healthcare, models trained on relatively homogeneous datasets, and populations poorly-representative of underlying diversity, limits generalisability and risks biased AI-based decisions. Here, we describe the landscape of AI in clinical medicine to delineate population and data-source disparities. Methods: We performed a scoping review of clinical papers published in PubMed in 2019 using AI techniques. We assessed differences in dataset country source, clinical specialty, and author nationality, sex, and expertise. A manually tagged subsample of PubMed articles was used to train a model, leveraging transfer-learning techniques (building upon an existing BioBERT model) to predict eligibility for inclusion (original, human, clinical AI literature). Of all eligible articles, database country source and clinical specialty were manually labelled. A BioBERT-based model predicted first/last author expertise. Author nationality was determined using corresponding affiliated institution information using Entrez Direct. And first/last author sex was evaluated using the Gendarize.io API. Results: Our search yielded 30,576 articles, of which 7,314 (23.9%) were eligible for further analysis. Most databases came from the US (40.8%) and China (13.7%). Radiology was the most represented clinical specialty (40.4%), followed by pathology (9.1%). Authors were primarily from either China (24.0%) or the US (18.4%). First and last authors were predominately data experts (i.e., statisticians) (59.6% and 53.9% respectively) rather than clinicians. And the majority of first/last authors were male (74.1%). Interpretation: U.S. and Chinese datasets and authors were disproportionately overrepresented in clinical AI, and almost all of the top 10 databases and author nationalities were from high income countries (HICs). AI techniques were most commonly employed for image-rich specialties, and authors were predominantly male, with non-clinical backgrounds. Development of technological infrastructure in data-poor regions, and diligence in external validation and model re-calibration prior to clinical implementation in the short-term, are crucial in ensuring clinical AI is meaningful for broader populations, and to avoid perpetuating global health inequity.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Though numerous publicly available datasets are currently available for AI researchers to use, most still lack diversity and the vulnerable patient populations continue to be underrepresented.”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [55]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Obtaining access to diverse external datasets for validation is often challenging due to privacy concerns, data-sharing restrictions, and variability of data quality across different institutions, however, is of paramount importance when models are intended for use beyond local environments25.”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Models optimized for majority groups often perform poorly for underrepresented patients, increasing misdiagnoses and inequitable treatment recommendations43,44.”
From Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare (2025) · cites this paper as [44]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In a recent review of the literature on clinical AI, Celi and colleagues reported that over half of the databases used to train models primarily reflected patients treated in the US and China [55].”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [55]
The cited source says what the claim attributes to it.
In the citing paper
“One study found that over half of all published clinical AI models in 2019 used training data from the US or China, which likely reflects the advanced technological infrastructure of these countries conducive to AI development [40].”
From Bias in medical AI: Implications for clinical decision-making (2024) · cites this paper as [40]
9 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Scoping studies: towards a methodological framework
Arksey, H., & O'Malley, L. (2005) · International Journal of Social Research Methodology · doi:10.1080/1364557032000119616 · Cited by 36,742
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Scoping studies: advancing the methodology
Levac, D., Colquhoun, H., & O'Brien, K. K. (2010) · Implementation Science · doi:10.1186/1748-5908-5-69 · Cited by 15,268
Munn, Z., Peters, M. D. J., Stern, C., Tufanaru, C., McArthur, A., & Aromataris, E. (2018) · BMC Medical Research Methodology · doi:10.1186/s12874-018-0611-x · Cited by 11,385
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
A guide to deep learning in healthcare
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312
Big Data and Machine Learning in Health Care
Beam, A. L., & Kohane, I. S. (2018) · JAMA · doi:10.1001/jama.2017.18391 · Cited by 2,506
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
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 1×
“[53] Despite high model accuracy within the centre in which it was built, authors found that the model performed poorly when applied to data from another institution within the same country.”
MethodRanibizumab for Diabetic Macular Edema
Nguyen, Q. D., Brown, D. M., Marcus, D. M., Boyer, D. S., Patel, S., Feiner, L., Gibson, A., Sy, J., Rundle, A. C., Hopkins, J. J., et al. (2012) · Ophthalmology · doi:10.1016/j.ophtha.2011.12.039 · Cited by 1,621
Ensuring fairness in machine learning to advance health equity.
Rajkomar, A., Hardt, M., Howell, M. D., Corrado, G., & Chin, M. H. (2018) · Annals of Internal Medicine · doi:10.7326/m18-1990 · Cited by 1,341
Benjamens, S., Dhunnoo, P., & Meskó, B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00324-0 · Cited by 1,215
Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020) · BMJ · doi:10.1136/bmj.m689 · Cited by 1,152
Roberts, M., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Aviles-Rivero, A. I., Etmann, C., McCague, C., Beer, L., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00307-0 · Cited by 1,044 · cited 1×
“None of the studies performed a proper assessment of model bias [48].”
BackgroundThe ethics of artificial intelligence
Bostrom, N., & Yudkowsky, E. (2014) · The Cambridge Handbook of Artificial Intelligence · doi:10.1017/cbo9781139046855.020 · Cited by 918
Roberts, M. T., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Avilés-Rivero, A. I., Etmann, C., McCague, C., Beer, L., et al. (2020) · Apollo (University of Cambridge) · doi:10.17863/cam.64000 · Cited by 895
The Role of Gender in Scholarly Authorship
West, J. D., Jacquet, J., King, M. M., Correll, S. J., & Bergstrom, C. T. (2013) · PLoS ONE · doi:10.1371/journal.pone.0066212 · Cited by 892
Rasmy, L., Xiang, Y., Xie, Z., Tao, C., & Zhi, D. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00455-y · Cited by 886
Brown, D. M., Nguyen, Q. D., Marcus, D. M., Boyer, D. S., Patel, S., Feiner, L., Schlottmann, P. G., Rundle, A. C., Zhang, J., Rubio, R. G., et al. (2013) · Ophthalmology · doi:10.1016/j.ophtha.2013.02.034 · Cited by 830
The impact of artificial intelligence in medicine on the future role of the physician
Ahuja, A. S. (2019) · PeerJ · doi:10.7717/peerj.7702 · Cited by 789
Publicly Available Clinical BERT Embeddings
Alsentzer, E., Murphy, J. R., Boag, W., Weng, W., Jin, D., Naumann, T., & McDermott, M. B. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03323 · Cited by 693
Deep Learning—A Technology With the Potential to Transform Health Care
Hinton, G. (2018) · JAMA · doi:10.1001/jama.2018.11100 · Cited by 667
Muehlematter, U. J., Daniore, P., & Vokinger, K. N. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30292-2 · Cited by 665
Machine Learning and Health Care Disparities in Dermatology
Adamson, A. S., & Smith, A. (2018) · JAMA Dermatology · doi:10.1001/jamadermatol.2018.2348 · Cited by 639
Adapting to Artificial Intelligence: Radiologists and Pathologists as Information Specialists
Jha, S., & Topol, E. J. (2016) · JAMA · doi:10.1001/jama.2016.17438 · Cited by 622
Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare
Cirillo, D., Catuara-Solarz, S., Morey, C., Guney, E., Subirats, L., Mellino, S., Gigante, A., Valencia, A., Rementeria, M. J., Chadha, A. S., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0288-5 · Cited by 553
Methods for Research Evidence Synthesis: The Scoping Review Approach
Sucharew, H. (2019) · Journal of Hospital Medicine · doi:10.12788/jhm.3248 · Cited by 489
The myth of generalisability in clinical research and machine learning in health care
Futoma, J., Simons, M., Panch, T., Doshi-Velez, F., & Celi, L. A. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30186-2 · Cited by 467
Self-citationComparison and benchmark of name-to-gender inference services
Santamaría, L., & Mihaljević, H. (2018) · PeerJ Computer Science · doi:10.7717/peerj-cs.156 · Cited by 401
Khan, S. M., Liu, X., Nath, S., Korot, E., Faes, L., Wagner, S. K., Keane, P. A., Sebire, N. J., Burton, M. J., & Denniston, A. K. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30240-5 · Cited by 334
Deep learning algorithm predicts diabetic retinopathy progression in individual patients
Arcadu, F., Benmansour, F., Maunz, A., Willis, J., Haskova, Z., & Prunotto, M. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0172-3 · Cited by 305
Gulshan, V., Rajan, R. P., Widner, K., Wu, D., Wubbels, P., Rhodes, T., Whitehouse, K., Coram, M., Corrado, G., Ramasamy, K., et al. (2019) · JAMA Ophthalmology · doi:10.1001/jamaophthalmol.2019.2004 · Cited by 303
Ethical limitations of algorithmic fairness solutions in health care machine learning
McCradden, M. D., Joshi, S., Mazwi, M., & Anderson, J. A. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30065-0 · Cited by 291
Artificial intelligence in radiation oncology: A specialty-wide disruptive transformation?
Thompson, R. F., Valdes, G., Fuller, C. D., Carpenter, C. M., Morin, O., Aneja, S., Lindsay, W. D., Aerts, H. J. W. L., Agrimson, B., Deville, C., et al. (2018) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2018.05.030 · Cited by 258
On the Prospects for a (Deep) Learning Health Care System
Naylor, C. D. (2018) · JAMA · doi:10.1001/jama.2018.11103 · Cited by 250
Geographic Distribution of US Cohorts Used to Train Deep Learning Algorithms
Kaushal, A., Altman, R., & Langlotz, C. (2020) · JAMA · doi:10.1001/jama.2020.12067 · Cited by 239
Artificial Intelligence for the Otolaryngologist: A State of the Art Review
Bur, A. M., Shew, M., & New, J. (2019) · Otolaryngology–Head and Neck Surgery · doi:10.1177/0194599819827507 · Cited by 172
Jain, H. K., Padmanabhan, B., Pavlou, P. A., & Raghu, T. S. (2021) · Information Systems Research · doi:10.1287/isre.2021.1046 · Cited by 170
Bardhan, I., Chen, H., & Karahanna, E. (2020) · MIS Quarterly · doi:10.25300/misq/2020/14644 · Cited by 167
Hwang, T. J., Kesselheim, A. S., & Vokinger, K. N. (2019) · JAMA · doi:10.1001/jama.2019.16842 · Cited by 156
Hong, J. C., Eclov, N. C. W., Dalal, N., Thomas, S. M., Stephens, S. J., Malicki, M., Shields, S., Cobb, A., Mowery, Y. M., Niedzwiecki, D., et al. (2020) · Journal of Clinical Oncology · doi:10.1200/jco.20.01688 · Cited by 103
Bursell, S.-E., Fonda, S. J., Lewis, D. G., & Horton, M. B. (2018) · PLOS ONE · doi:10.1371/journal.pone.0198551 · Cited by 68
Trends and Focus of Machine Learning Applications for Health Research
Beaulieu‐Jones, B. K., Finlayson, S. G., Chivers, C., Chen, I. Y., McDermott, M. B. A., Kandola, J., Dalca, A. V., Beam, A. L., Fiterau, M., & Naumann, T. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.14051 · Cited by 68
Lebovitz, S., Levina, N., & Lifshitz-Assaf, H. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16564 · Cited by 49
Generalisability through local validation: overcoming barriers due to data disparity in healthcare
Mitchell, W. G., Dee, E. C., & Celi, L. A. (2021) · BMC Ophthalmology · doi:10.1186/s12886-021-01992-6 · Cited by 33
Self-citationPre-training technique to localize medical BERT and enhance biomedical BERTPreprint
Wada, S., Takeda, T., Manabe, S., Konishi, S., Kamohara, J., & Matsumura, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07202 · Cited by 32
Wada, S., Takeda, T., Okada, K., Manabe, S., Konishi, S., Kamohara, J., & Matsumura, Y. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102889 · Cited by 27
Artificial Intelligence in Radiation Oncology Imaging
Thompson, R. F., Valdés, G., Fuller, C. D., Carpenter, C. M., Morin, O., Aneja, S., Lindsay, W. D., Aerts, H. J. W. L., Agrimson, B., Deville, C., et al. (2018) · International Journal of Radiation Oncology*Biology*Physics · doi:10.1016/j.ijrobp.2018.05.070 · Cited by 26
A Pre-Training Technique to Localize Medical BERT and to Enhance Biomedical BERTPreprint
Wada, S., Takeda, T., Manabe, S., Konishi, S., Kamohara, J., & Matsumura, Y. (2020) · doi:10.21203/rs.3.rs-103477/v1 · Cited by 18
Discrepancies in Stroke Distribution and Dataset Origin in Machine Learning for Stroke
Velagapudi, L., Mouchtouris, N., Baldassari, M. P., Nauheim, D. O., Khanna, O., Saiegh, F. A., Herial, N. A., Gooch, M. R., Tjoumakaris, S. I., Rosenwasser, R. H., et al. (2021) · Journal of Stroke and Cerebrovascular Diseases · doi:10.1016/j.jstrokecerebrovasdis.2021.105832 · Cited by 17
Research works printed but not linked: 8
- 2018, Oxford english dictionary.
- M Tempelier, 2015, framework for guiding and evaluating literature reviews. Communications of the association for information systems, Communications of the Association for Information Systems, 37
- Pubmed overview. https://pubmed.ncbi.nlm.nih.gov/about/. Accessed February, 2021.
- Covidence—better systematic review management. Covidence 2021; https://www.covidence.org/. Accessed April, 2020.
- B Hao, 2020, Enhancing clinical bert embedding using a biomedical knowledge., Paper presented at: 28th International Conference on Computational Linguistics
- K. Wiggers, 2020, Openai’s massive gpt-3 model is impressive, but size isn’t everything, The Machine: Making Sense of AIAccessed October
- QD Nguyen, 2012, Ranibizumab for diabetic macular edema, Ophthalmology, 119, 0, 10.1016/j.ophtha.2011.12.039 · DOI · Paper page
- M West, 2006, Aup faculty gender equity indicators 2006
Cited by
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., Weicken, E., Asselbergs, F. W., Prior, F., Collins, G. S., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081554 · Cited by 957
“For example, the FAIR guideline 10 for data management has been widely adopted by researchers, organisations, and authorities, as the principles provide a structured framework for standardising and enhancing the tasks of data collection, curation, organisation, and storage.”
Bias in artificial intelligence algorithms and recommendations for mitigation
Nazer, L. H., Zatarah, R., Waldrip, S., Ke, J. X. C., Moukheiber, M., Khanna, A. K., Hicklen, R. S., Moukheiber, L., Moukheiber, D., Ma, H., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000278 · Cited by 621
Self-citationBias in medical AI: Implications for clinical decision-making
Cross, J. L., Choma, M. A., & Onofrey, J. A. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000651 · Cited by 607
Bias recognition and mitigation strategies in artificial intelligence healthcare applications
Hasanzadeh, F., Josephson, C. B., Waters, G., Adedinsewo, D., Azizi, Z., & White, J. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01503-7 · Cited by 320
“Obtaining access to diverse external datasets for validation is often challenging due to privacy concerns, data-sharing restrictions, and variability of data quality across different institutions, however, is of paramount importance when models are intended for use beyond local environments 25 .”
InfluentialExplainable Artificial Intelligence (XAI): Concepts and Challenges in Healthcare
Hulsen, T. (2023) · AI · doi:10.3390/ai4030034 · Cited by 305
“The first one is “small” data, resulting in bias [7].”
Background
Metadata
- Authors
- Celi, L. A., Cellini, J., Charpignon, M.-L., Dee, E. C., Dernoncourt, F., Eber, R., Mitchell, W. G., Moukheiber, L., Schirmer, J., Situ, J., Paguio, J., Park, J., Wawira, J. G., Yao, S., & Data, F. M. C.
- Affiliations
- Beth Israel Deaconess Medical Center (US)
- Harvard University (US)
- Massachusetts Institute of Technology (US)
- Adobe Systems (United States) (US)
- Université de Montpellier (FR)
- Jefferson Einstein Philadelphia Hospital (US)
- Corresponding author
- Mitchell, William Greig
- ORCID
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2022-03-31
- Volume
- 1
- Issue
- 3
- Pages
- e0000022
- ISSN
- 2767-3170 (ISSN-L)
- PMC
- PMC9931338
- OpenAlex
- W4220839569
- Cited by
- 576
- References
- 52
- Citations by year
- 2026: 198 · 2025: 181 · 2024: 117 · 2023: 70 · 2022: 10
- FWCI
- 28.35
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLOS Digital Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- HAL (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Funders
- National Institutes of Health (5r01eb017205-07, R01-EB017205, EB017205-01A1, EB017205)
- National Institute of Biomedical Imaging and Bioengineering (R01-EB017205, EB017205-01A1, EB017205)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- algorithmic bias, health care disparities, generalizability, data representativeness, author demographics, author nationality, medical specialties, radiology, high-income countries, global health inequities, external validation, model recalibration, transfer learning, BioBERT
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.