Bias in medical AI: Implications for clinical decision-making
Open accessThe DOI matches its Crossref record; 124 of the 124 references it cites were found in a registry or an index; 30 of the 140 sources its claims cite were checked for support.
Abstract
Biases in medical artificial intelligence (AI) arise and compound throughout the AI lifecycle. These biases can have significant clinical consequences, especially in applications that involve clinical decision-making. Left unaddressed, biased medical AI can lead to substandard clinical decisions and the perpetuation and exacerbation of longstanding healthcare disparities. We discuss potential biases that can arise at different stages in the AI development pipeline and how they can affect AI algorithms and clinical decision-making. Bias can occur in data features and labels, model development and evaluation, deployment, and publication. Insufficient sample sizes for certain patient groups can result in suboptimal performance, algorithm underestimation, and clinically unmeaningful predictions. Missing patient findings can also produce biased model behavior, including capturable but nonrandomly missing data, such as diagnosis codes, and data that is not usually or not easily captured, such as social determinants of health. Expertly annotated labels used to train supervised learning models may reflect implicit cognitive biases or substandard care practices. Overreliance on performance metrics during model development may obscure bias and diminish a model’s clinical utility. When applied to data outside the training cohort, model performance can deteriorate from previous validation and can do so differentially across subgroups. How end users interact with deployed solutions can introduce bias. Finally, where models are developed and published, and by whom, impacts the trajectories and priorities of future medical AI development. Solutions to mitigate bias must be implemented with care, which include the collection of large and diverse data sets, statistical debiasing methods, thorough model evaluation, emphasis on model interpretability, and standardized bias reporting and transparency requirements. Prior to real-world implementation in clinical settings, rigorous validation through clinical trials is critical to demonstrate unbiased application. Addressing biases across model development stages is crucial for ensuring all patients benefit equitably from the future of medical AI.
Overview
CoChat Summary
TL;DR
This narrative review argues that bias in medical AI arises and compounds across the entire lifecycle—training data, model development and evaluation, deployment, and publication—and can worsen clinical decisions and health disparities. It catalogs mitigation strategies including diverse data collection, statistical debiasing, subgroup evaluation, interpretability, bias reporting, and clinical-trial validation.
Key findings
- Bias can enter at multiple stages: imbalanced sample sizes, nonrandomly missing data, uncaptured social determinants of health, biased labels, race/ethnicity in clinical algorithms, overreliance on whole-cohort performance metrics, publication biases, and implementation/end-user biases.
- The review cites specific examples and numbers: over half of published clinical AI models in 2019 used data from the US or China; radiology accounted for over 40% of AI publications in 2019; authors were 75% male; a MIMIC-III mortality model yielded recall rates as low as 25% under imbalanced racial representation; and the Epic Sepsis Model missed two-thirds of sepsis cases after deployment.
- Mitigation strategies discussed include large diverse data sets, oversampling methods such as SMOTE and ADASYN, imputation, SDoH capture, expert consensus labeling, subgroup analysis, bias-centered metrics like equalized odds and predictive parity, interpretability methods such as SHAP and LIME, adversarial debiasing, ongoing monitoring, and clinical trials for AI validation.
- Medical large language models pose unique bias risks because they are autoregressive, can reproduce biased or inaccurate training content, cannot assess their own outputs, and may generate inconsistent recommendations; statistical debiasing methods for clinical LLMs remain limited.
Methods
- Narrative review, not a systematic review, synthesizing literature and real-world or hypothetical examples across diverse medical domains and stages of the AI development pipeline.
- Includes Table 1 summarizing bias types by development stage, illustrative examples, potential clinical consequences, and mitigation strategies.
- No primary data collection, systematic search protocol, or quantitative meta-analysis is reported; the work draws on cited studies and examples.
Limitations
- Stated in the paper: more research is needed; there is a lack of standardized bias reporting guidelines; there are no explicit FDA regulations examining fairness or bias in medical AI outputs; and statistical debiasing methods for real-world clinical LLMs remain limited.
- Evident from the text: as a narrative review, it lacks systematic search and selection criteria and does not quantitatively synthesize evidence; examples are illustrative or hypothetical and not exhaustive; and the proposed mitigations are not empirically validated in this paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
17 Valid · 2 Not valid · 65 Not checked · 42 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Fewer studies have concentrated specifically on the implications and consequences of biased AI in healthcare [19–22].”
§ Bias in medical AI: Implications for clinical decision-making > Related work
What the sources say
- Not checked yetcites [19] RB Parikh, 2019, Addressing bias in artificial intelligence in health care, JAMA source
- Supportedcites [20] MD Abràmoff, 2023, Considerations for addressing bias in artificial intelligence for health equity, NPJ Digit Med source
The cited paper is an example of a study focused on biased AI in healthcare and its consequences. Its Introduction describes AI exacerbating health disparities and contributing to worse outcomes for Black patients; the “Bias in the healthcare process” section examines unequal outcomes across groups. The citation supports identifying this paper as one of the studies, rather than establishing a count of how many such studies exist. (LLM, conf=0.86)
- Partly supportedcites [21] R Daneshjou, 2021, Lack of transparency and potential bias in artificial intelligence data sets and algorithms: a scoping review, JAMA Dermatol sourceExperimental — accuracy not yet measured
The Discussion says that few dermatology AI studies report patient race, ethnicity, or skin tone, limiting assessment of potential bias. That supports a narrower gap in studying bias, but the paper does not establish that fewer studies across healthcare have examined the implications and consequences of biased AI. (LLM, conf=0.82)
- Not checked yetcites [22] AS Albahri, 2023, A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion., Inf Fusion. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Standardized reporting checklists such as the Prediction Model Risk of Bias Assessment (PROBAST) tool have been developed to assess the risk of imbalanced data biases, which allows both developers and downstream users (e.g., physicians, hospitals) to better understand the suitability and limitations of AI-based systems in specific clinical settings [54–56].”
§ Bias in medical AI: Implications for clinical decision-making > Biases in training data > Imbalanced sample sizes
What the sources say
- Not checked yetcites [54] RF Wolff, 2019, PROBAST: a tool to assess the risk of bias and applicability of prediction model studies, Ann Intern Med source
- Partly supportedcites [55] T Hernandez-Boussard, 2020, MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care., J Am Med Inform Assoc sourceExperimental — accuracy not yet measured
The Introduction and General Principles of the MINIMAR Design say that reporting training-data characteristics can reveal potential biases and help assess whether an AI model generalizes to a clinical population. But the paper proposes MINIMAR; the passages found do not identify PROBAST or say that PROBAST was developed to assess biases from imbalanced data. No page numbers are available in our copy. (LLM, conf=0.83)
- Could not verifycites [56] Szczekocka E, Tarnec C, Pieczerak J, editors. Standardization on bias in Artificial Intelligence as industry support. 2022 IEEE International Conference on Big Data (Big Data); 2022: IEEE. sourceExperimental — accuracy not yet measured
The Standardization Specifics section says standards could help identify data-related biases, but it does not discuss PROBAST or a reporting checklist. Searches for PROBAST, imbalanced data, and clinical settings found no passage establishing the claimed purpose or use of that tool. (LLM, conf=0.76)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The researchers found that imbalanced representation of racial groups had a significant effect on model performance (yielding recall rates as low as 25%), raising critical concerns for the model’s potential application in real clinical settings [44].”
§ Bias in medical AI: Implications for clinical decision-making > Biases in training data > Imbalanced sample sizes
What the sources say
- Partly supportedcites [44] E Röösli, 2022, Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model., Sci Data. sourceExperimental — accuracy not yet measured
The Discussion reports significantly worse prediction performance for Black patients and says their low representation might partly explain the bias; it does not establish that imbalanced racial representation caused the performance gap. The Discussion also says the model identified only every fourth to fifth high-risk patient, but that low recall concerns the high-risk class overall, not a racial group. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Furthermore, the degree of practitioner misclassification can vary along sociodemographic factors.”
§ Bias in medical AI: Implications for clinical decision-making > Biases in training data > Data labels and misclassification
What the sources say
- Supportedcites [84] GH Rauscher, 2013, Potentially missed detection with screening mammography: does the quality of radiologist’s interpretation vary by patient socioeconomic advantage/disadvantage?, Ann Epidemiol source
The INTRODUCTION states the goal was 'to examine whether variation in the quality of mammography interpretation as performed by the original reading radiologist varied by patient sociodemographic characteristics,' i.e. radiologist (practitioner) error by sociodemographic group. The RESULTS (p. 3, Table 3 discussion) report that potentially missed detection differed by minority ethnicity (+17 pp), income, education and lack of private insurance (+30 pp), and the DISCUSSION concludes the observed racial/ethnic and socioeconomic disparities 'shed light on differences in the quality of interpretation for different racial/ethnic and sociodemographic groups.' The Abstract's CONCLUSIONS affirm the association, so the hedged claim that practitioner misclassification 'can vary' along sociodemographic factors is supported; only the education association was attenuated in the selection-bias sensitivity analysis. (LLM, conf=0.90)
- Not checked yetcites [85] AM Kilbourne, 2005, Care without coverage: too little, too late., J Natl Med Assoc
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“There are several well-documented instances of insufficient evidence for race and ethnicity to be used as predictive factors in models.”
§ Bias in medical AI: Implications for clinical decision-making > Biases in training data > Race and ethnicity in clinical algorithms
What the sources say
- Partly supportedcites [92] MA Marzinke, 2022, Limited evidence for use of a black race modifier in eGFR calculations: a systematic review, Clin Chem sourceExperimental — accuracy not yet measured
The Discussion (page unavailable) concludes that there is little evidence for including a Black race modifier in eGFR calculations. This documents an instance of insufficient evidence for using race in a model, but the paper does not establish the broader claim of several instances involving race and ethnicity across models. (LLM, conf=0.85)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
65 more claims · 8 with their cited sources checked
Create a free account to see all 126 claims and to verify the 110 references still open.
- It may state two separate claims as one. 41
- Probably not a substantial claim. 28
- The quote only partly states this claim. 1
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
“Generating educational resources without clinical context review risks reinforcing data biases [172]”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [172]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In contrast, ensemble classification, combining multiple models, demonstrated improved accuracy and robustness [21,22].”
From Machine Learning in Maternity: Early Diagnosis of Placenta Accreta Spectrum (2026) · cites this paper as [22]
Experimental — accuracy not yet measured
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 1×
“…which generates synthetic examples for the minority class by interpolating between existing minority class instances, and Adaptive Synthetic Sampling (ADASYN), which uses a similar method to SMOTE but focuses more on examples that are harder to classify (near the decision boundary) [49,50].”
MethodA Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
Crenshaw, K. (2018) · Living with Contradictions · doi:10.4324/9780429499142-5 · Cited by 7,232
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“In reality, however, AI models are frequently found to be biased toward certain patient groups, leading to disparities not only in performance but also in potential or actual clinical benefits [7–9].”
BackgroundA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812 · cited 1×
“The topic of bias in AI has garnered significant attention in recent years, with multiple review papers addressing different aspects of this critical issue [14–18].”
BackgroundCrenshaw, K. (1998) · Feminism And Politics · doi:10.1093/oso/9780198782063.003.0016 · Cited by 5,672
Social determinants of health inequalities
Marmot, M. (2005) · The Lancet · doi:10.1016/s0140-6736(05)71146-6 · Cited by 5,086
ADASYN: Adaptive synthetic sampling approach for imbalanced learning
He, H., Bai, Y., Garcia, E. A., & Li, S. (2008) · 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) · doi:10.1109/ijcnn.2008.4633969 · Cited by 4,521
Research works printed but not linked: 12
- Food, Administration D., 2019, Proposed regulatory framework for modifications to Artificial Intelligence/Machine Learning (AI/ML)-based Software as a Medical Device.
- D Roselli, 2019, editors. Managing bias in AI. Companion proceedings of the 2019, world wide web conference
- KPUL McFarling, 2024, Doctors use problematic race-based algorithms to guide care every day. Why are they so hard to change?, STAT
- Ribeiro MT, Singh S, Guestrin C. Model-agnostic interpretability of machine learning. arXiv preprint arXiv:160605386. 2016.
- Raji ID, Bender EM, Paullada A, Denton E, Hanna A. AI and the everything in the whole wide world benchmark. arXiv preprint arXiv:211115366. 2021.
- Chauhan VK, Clifton L, Salaün A, Lu HY, Branson K, Schwab P, et al. Sample Selection Bias in Machine Learning for Healthcare. arXiv preprint arXiv:240507841. 2024.
- Yang S, Wang Y, Chu X. A survey of deep learning techniques for neural machine translation. arXiv preprint arXiv:200207526. 2020.
- Topal MO, Bas A, van Heerden I. Exploring transformers in natural language generation: Gpt, bert, and xlnet. arXiv preprint arXiv:210208036. 2021.
- Schmidgall S, Harris C, Essien I, Olshvang D, Rahman T, Kim JW, et al. Addressing cognitive bias in medical language models. arXiv preprint arXiv:240208113. 2024.
- Ebrahimi S, Chen K, Asudeh A, Das G, Koudas N. AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs. arXiv preprint arXiv:240300198. 2024.
- Li J, Tang Z, Liu X, Spirtes P, Zhang K, Leqi L, et al. Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework. arXiv preprint arXiv:240308743. 2024.
- Zhang Y-F, Yu W, Wen Q, Wang X, Zhang Z, Wang L, et al. Debiasing large visual language models. arXiv preprint arXiv:240305262. 2024.
Cited by
Items 501–600 of 716
Ilampari, M., Faruk, M. N., Berry, R., Verma, A., Ranga, J., & Kumar, Y. (2026) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla67915.2026.11522341
Khakpoor, F. L., van der Vliet, W., Deng, J. D., Wang, Y., & Pat, N. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.25.727742
Prior Authorization and Clinical Authority: Time to Recalibrate?
Weiland, G. (2026) · Annals of Internal Medicine · doi:10.7326/annals-26-00918
Hsiao, C., Cheng, Y.-R., Yang, C., & Hsu, F.-S. (2026) · medRxiv · doi:10.64898/2026.05.29.26354442
Artificial intelligence for early sepsis detection and dynamic prognostication in onco-critical care
Sirohiya, P., Maurya, P., Arora, S., Ratre, B. K., Singh, R., & Kumar, B. (2026) · World Journal of Critical Care Medicine · doi:10.5492/wjccm.120560
Paul, B. M., Kannan, G., & Thangaraj, P. (2026) · ACS Applied Engineering Materials · doi:10.1021/acsaenm.6c00314
Toward personalised cancer care: AI in precision and molecular oncology
Sinha, A., Anzar, D., Owusu-Boampong, A. B., Nkrumah-Boateng, P. A., Mannan, K. M., Ali, S. H., Roy, S., & Wireko, A. A. (2026) · European journal of medical research · doi:10.1186/s40001-026-04670-9
“Alongside regulatory efforts, emerging research proposes structured pipelines for continuous bias auditing to monitor and mitigate demographic performance disparities throughout model development and deployment, thereby reducing the risk of perpetuating inequalities in cancer care [183, 184].”
Ethical and Legal Implications in Medical AI
Khullar, S., Ahmed, I., Kapoor, S. K., Joshi, M. L., & Arora, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-2173-6.ch005
Explainable and Trustworthy AI for Surgical Systems
Mahajan, P., & Anandaram, H. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0358-9.ch002
Sicras-Mainar, A. (2026) · Medicina de Familia SEMERGEN · doi:10.1016/j.semerg.2026.102786
Rong, Z., Si, H., Bai, W., Wang, D., Sun, L., Tian, H., 闫双通, Miao, X., Kang, X., & Hou, X. (2026) · Artificial Intelligence in Health · doi:10.36922/aih026130031
Machine learning-integrated private blockchain framework for bias detection in clinical trials data
Shetty, S. S., Pushpalatha, K., & Lokesh, K. S. (2026) · Array · doi:10.1016/j.array.2026.101002
Kim, S.-J., Kim, D., Ko, J., Zan, X., Wong, K. L., Mao, Y., Kaur, L., 남현준, & Lee, J. W. (2026) · Digital Health · doi:10.1177/20552076261458965
Iglesias, V. S., Modi, N. J., Purackal, R. S., Shoukat, K., Koyun, A., Nangolo, M. N., & Park, K. (2026) · Westcliff International Journal of Applied Research · doi:10.47670/wuwijar20262vnrkamk
The Role of Artificial Intelligence in Medical Education and Training
Scielzo, S. A., & Kazi, S. (2026) · Rheumatic Disease Clinics of North America · doi:10.1016/j.rdc.2026.04.003
Artificial intelligence for gastric cancer: Advances and current status in diagnosis and therapy
Chi, Z.-C. (2026) · World Chinese Journal of Digestology · doi:10.11569/wcjd.v34.i5.345
Lyle, K., Samuel, G. N., & Lucassen, A. (2026) · Sociology of Health & Illness · doi:10.1111/1467-9566.70205
“Algo-rithmic diagnostic systems, likewise, often exhibit differential accuracy across demographic groups (Cross et al. 2024).”
Artificial Intelligence in Social Work: Bridging Technology and Humanity
An, R., & Lindsey, M. A. (2026) · Springer eBooks · doi:10.1007/978-3-032-18443-6 · Cited by 1
Yang, Y., Huang, J., & An, R. (2026) · Springer eBooks · doi:10.1007/978-3-032-18443-6_21 · Cited by 1
Seghier, M. L. (2026) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.70393
Bignami, E. G., Bellini, V., Lanza, R., & Russo, M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01616-2
“If a physician overrides an AI alert and an adverse event occurs, or conversely, follows a flawed AI recommendation resulting in harm, the legal ramifications remain largely uncharted [22].”
Nona, P. J., Firos, J. R. B., Zografos, C., Schuuring, M. J., Bhatt, A., & Andrikopoulou, E. (2026) · Current Heart Failure Reports · doi:10.1007/s11897-026-00766-9 · Cited by 1
“Algorithm design can also influence bias when built on biased data [ 27 ].”
Guillen-Ramirez, H., Lucas, K. L., Wintsch, Y. M., Blatter, T. U., Triep, K., Endrich, O., & Beldi, G. (2026) · Journal of the American Medical Informatics Association · doi:10.64898/2026.06.15.26355656
AI and Its Shifting Roles in the Therapeutic Relationship: Implications for Precision Medicine
Igoumenidis, M., & Velonaki, V. S. (2026) · Journal of Personalized Medicine · doi:10.3390/jpm16060324
“Apart from active self-management of their health, individuals can also use AI to enhance their health literacy and medical information-seeking abilities [42], further increasing their autonomy levels.”
Jose, A., Mohan, R., & Kaithathara, S. T. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-2373-0.ch005
Assuring AI safety for managing risk of myocardial infarction for patients with type 2 diabetes
Ozturk, B. (2026) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)
Time-Aware Contrastive Transformer for Longitudinal Patient Representation LearningPreprint
Heinolainen, A., Tran, L., Arora, A., Renkonen, S., Renkonen, R., & Koskinen, M. (2026) · medRxiv · doi:10.64898/2026.06.23.26356236
Reflection: AI as a catalyst for change in postgraduate medical education
Adam, S., & Burch, V. C. (2026) · Journal of the Colleges of Medicine of South Africa · doi:10.4102/jcmsa.v4i1.413
Transforming healthcare with large language models: Innovation, integration, and impact
Joshi, G., Ghai, B., Goutam, N., & Joshi, N. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44344-2.00010-8
Singh, P., Saifi, N., Thayanithi, C. A., Elipe, A., & Peacock, R. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44344-2.00023-6
Indebetou, D., & Piehl, V. (2026) · Lund University Publications Student Papers (Lund University)
A quality improvement roadmap for scalable AI implementation in healthcare
Arnaout, A., Abrahams, B., Hinada, P., & McKenzie, M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01447-1
Decoding Algorithmic Inequity: Reversing the Generative AI Racial Divide in Healthcare
Davidson, J., Fowe, I. E., Oderinde, A., & Fadeyi, S. A. (2026) · Clinical Therapeutics · doi:10.1016/j.clinthera.2026.06.015 · Cited by 2
Just Don’t Make It Worse: A custom GPT to develop Generative AI literacy in specialized translation
Herget, K., Yeung, J.-E., & Rufrano, M. (2026) · International Conference on Higher Education Advances (HEAd) · doi:10.4995/head26.2026.21626
AI Enhanced Telemedicine: A Double-Edged Sword for Healthcare Equity in the Post-COVID Era
Fatima, S. S., Ahmed, A., Shakeel, A., & Zehra, W. (2026) · International Journal of Digital Health and Telemedicine · doi:10.51137/wrp.ijdht.858
Artificial intelligence for child health: current capabilities and the next frontier
Dimitri, P. (2026) · Archives of Disease in Childhood · doi:10.1136/archdischild-2026-330388
“41 57 59 As an example, ChatGPT-4.”
Efficient Diagnostic System for Rural Healthcare Using AI and Medical Image Processing
Rajulu, G. G., Umamahesh, S., Shivapranay, B., & Santhoshkumar, S. P. (2025) · International Conference on Emerging Research in Computational Science (ICERCS) · doi:10.1109/icercs65898.2025.11581136
“James L Cross et al., (2024) assessed bias in AI and ML diagnostic systems, indicating that although AI can help reduce cognitive biases, the use of training data that is unrepresentative or imbalanced can inadvertently magnify existing healthcare inequities [13].”
The role of artificial intelligence in reducing physician cognitive errors in emergency medicine
Геруш, Н. І. (2026) · DSpace BSMU
Bernard, J., Gotz, D., Laramee, R. S., Miksch, S., Morgenshtern, G., Raidou, R. G., & Arleo, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.00542
“This concern aligns with work documenting how biases compound across the AI development pipeline, from data acquisition through deployment, with downstream effects on clinical decision quality and healthcare disparities [14,15].”
Shin, H. D., Ronquillo, C., Lee, J., Lokmic‐Tomkins, Z., Reid, L., You, S. B., Davies, S., Block, L. J., Özbay, İ., Lukitasari, M., et al. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106582
Rizvi, D., & Jooste, K. R. (2026) · The Lancet Digital Health · doi:10.1016/j.landig.2026.101052
Governing Digital Health Assets in the AI Era: Antitrust, IP Rights, and Consumer ProtectionPreprint
Hosseini, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7043899
Human factor integrated MMSE for improved cognitive screening
Zhang, M., Li, W., Hong, C., Cui, Q., Sun, A., Jia, H., & Pan, Y. (2026) · npj Dementia · doi:10.1038/s44400-026-00117-4
“Data processing standardized variable types, enforced the valid threshold used in the MMSE total score, and applied strict completeness criteria for MMSE item responses and pre-speci fi ed human factor variables to minimize biases 45 from differential missingness.”
Artificial intelligence in pharmacy and medicine: From drug discovery to patient care
Ata, T., Al-Ani, I. H., Abdel-Qader, D. H., Abu‐Huwaij, R., Alrubaye, M. A., Daoud, E., Basheti, I. A., & Daiyyh, W. A. (2026) · Artificial Intelligence in Health · doi:10.36922/aih026210048
Heroza, R. I. (2026) · Open Access at Essex (University of Essex) · doi:10.5526/err-00043533
Buali, H. F., Abushloa, T., Shaibani, A. A., Bastawisy, A., Farouqi, U. S., & Rafie, M. A. (2026) · Cureus · doi:10.7759/cureus.112349
A call to action for an equitable global genomic system
Mascalzoni, D., Niedbalski, S., Boughtwood, T. F., Kato, K., Staunton, C., Ramsay, M., Ross, A. L., & Tayoun, A. N. A. (2026) · Nature Genetics · doi:10.1038/s41588-026-02667-y
Γκασιαβέλης, Π., Papathanasiou, I. V., Malliarou, M. M., & Mavroforou, A. (2026) · International Medical Education · doi:10.3390/ime5030062
“Contemporary healthcare is increasingly shaped by digital transformation, artificial intelligence (AI), machine learning technologies and data-driven Medical practices which are rapidly changing both clinical decision-making and healthcare delivery [29–32].”
The Gut–Nutrient–Genome Axis: A Host-Integrated Perspective on Genomic Instability in Cancer
Owen, R. H., & Ravindran, S. (2026) · Onco · doi:10.3390/onco6030032
“Equitable access, longitudinal data capture burden, privacy protection, algorithmic https://doi.org/10.3390/onco6030032 bias, interpretability of computational systems, regulatory oversight, and accountability within AI-assisted analytical environments all represent major considerations [51,61].”
InfluentialInvited Commentary: Transforming Occupational Therapy Research With Artificial Intelligence
Wolpert, R., Liew, S., Pickett, K. A., & Wu, C.-Y. (2026) · OTJR Occupational Therapy Journal of Research · doi:10.1177/15394492261464096
Li, J., Lian, S., Liu, Y., Yang, X., Liu, D., Chen, J., & Xiong, H. (2026) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2026.1865643
Chen, W., Bian, M., & Shu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3485-1_23
Responsible Health-AI: Complex scenarios from a humanities perspective
George, S. K. (2026) · Indian Journal of Medical Ethics · doi:10.20529/ijme.2026.042
“The dataset of the Melanoma Project is apparently biased towards “light-skinned images from patients in the US, Europe, and Australia (imbalanced sample bias)” and does not predict accurately for persons with darker skin colour [18: p 4].”
AI ASSISTANCE OR OVERRELIANCE? ANALYZING ESP STUDENTS’ CRITICAL USE OF GENERATIVE AI
Ajiza, M., Yuliasri, I., Pratama, H., & Wahyuni, S. (2026) · English Review Journal of English Education · doi:10.25134/englishreview.v14i2.153
Fabricated Foundations: Synthetic Data and Bias in Machine Learning
Gupta, D., Khamidova, M., Norov, J., Rakhmonkulova, F., Gaffarovich, N. M., Ashirova, A. I., & Bayramovich, S. B. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0368-8.ch001
The peripheral machine: Algorithmic sovereignty and the fractured geographies of sense
Grassi, E. (2026) · Journal of Emerging Perspectives · doi:10.36253/jep-20881
Human-AI Synergy in Clinical Decision-Making: Balancing Innovation, Safety and Patient-Centric Care
Eskandar, K. (2026) · Artificial intelligence · doi:10.5772/intechopen.1014561
AI-Assisted Smear Microscopy for Early Tuberculosis Diagnosis in Resource-Limited Settings
Manish, D., Selvarasu, B., & Ray, S. (2026) · IEEE International Conference on Intelligent Technologies for a Sustainable and Inclusive Future (ICITSIF) · doi:10.1109/icitsif69060.2026.11608525
“According to WHO, before integrating a diagnostic system utilizing artificial intelligence with a program, it needs to pass a strict clinical validation and monitoring process [24].”
Neto, J. B. D., & Urtubeny, L. S. (2026) · Derecho y cambio social. · doi:10.54899/dcs.v23i92.6301
Human Vulnerability in Interaction with AI in European Private Law
Amodio, C., & Diurni, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-93247-2 · Cited by 2
Arcuri, M. A. (2025) · Springer eBooks · doi:10.1007/978-3-031-93247-2_8
Alevizakos, V., Gaudin, R., Ghanad, I., von See, J., von See, T., Eggmann, F., & von See, C. (2026) · BMC Oral Health · doi:10.1186/s12903-026-09368-2
“This variability highlights an important methodological consideration: even among trained specialists, assessment of AI-generated clinical content can be subjective and influenced by individual thresholds for accuracy, clinical sufficiency, and interpretability [19].”
Emovon, A., Driggers-Jones, L., Engelhard, M., Maslow, G., Dawson, G., Goldstein, B. A., & Franz, L. (2026) · JAMIA Open · doi:10.1093/jamiaopen/ooag145
Wasim, M., Wang, Y., & Ma, G. (2026) · Orphanet Journal of Rare Diseases · doi:10.1186/s13023-026-04513-0
“For example, the FairSeg dataset comprises 76% white patients with only 24% Black and Asian patients, reducing model effectiveness for minorities and potentially exacerbating healthcare disparities [119–121].”
Building robust counterfactual explanations with statistical guarantees
Carrizosa, E., & Navas-Orozco, A. (2026) · EURO Journal on Computational Optimization · doi:10.1016/j.ejco.2026.100135
Liu-Galvin, R. E., Tran, K., Khan, M., Eadon, M. T., Sarder, P., & Strekalova, Y. L. (2026) · medRxiv · doi:10.64898/2026.07.24.26358862
Connor, M., & Kagan, O. (2026) · Seminars in Oncology Nursing · doi:10.1016/j.soncn.2026.152307
A data-driven machine learning model for effective diabetes diagnosis
Shobha, T., Pradeep, S., Patil, S., Subramanya, J., & Mitra, G. B. S. (2026) · Scientific Reports · doi:10.1038/s41598-026-63505-z
“Detection and alleviating bias especially in clinical decision-making are crucial to avoid inconsistencies and warrant all patients benefit equally 11 .”
Assessing BRCA Subtyping fairness with Ancestry-aware and Secure Federated Learning
Paygambar, K., Bendoukha, A.-A., Stan, O., Mziou-Sallami, M., & Meyer, V. (2026) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3807503.3819441
Basta, K., Zahid, U., Hardalupas, M., & Vilić, D. (2026) · BMJ Digital Health & AI · doi:10.1136/bmjdh-2026-000087
Grancia, M. K. (2026) · Advances in Public Health · doi:10.1155/adph/6348429
Eshun, I. (2026) · Journal of Aging and Health · doi:10.1177/08982643261474654
Yousaf, F. (2026) · Journal of Artificial Intelligence and Robotics · doi:10.61577/jaiar.2025.1000017
Artificial intelligence in diagnostic dentistry: technology and Islamic ethical compliance
Rosali, M. M., Abdullah, A. A. A., Abdullah, S. M., & Ramlan, N. (2026) · International Journal of Orofacial and Health Sciences · doi:10.31436/ijohs.v7i2.505
“…and repetitive patterns exacerbate biases and overfitting, and need rigorous external validation on diverse datasets to demonstrate robustness and prevent diagnostic errors (Cross et al. , 2024; Shoorgashti et al. , 2025; Albalawi & Abalkhail, 2022; Gracea et al. , 2025; Kim et al. , 2024).”
Beyond ISO Standards: What Really Drives EHRS Adoption in Developing Healthcare Systems
Shatem, M., Keoy, K. H., & Yeo, S. F. (2026) · Journal of Logistics Informatics and Service Science · doi:10.33168/jliss.2026.0806
Inzunza-González, E., & Stasolla, F. (2026) · Technologies · doi:10.3390/technologies14080475
Uzoechina, G., & Osajiuba, T. (2026) · BMC Artificial Intelligence · doi:10.1186/s44398-026-00035-8
“The majority of the current literature is still focused on technical performance, with relatively little evidence supporting downstream clinical benefit [51].”
Wang, C., Liu, Z., Jiang, Y., Zhang, T., Wang, H., Xue, T., & Liu, P. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1850996
Malik, D. A., Sirjani, B. B., Gaskins, J., Martin, R. C. G., & Javid, M. (2026) · Surgical Oncology Insight · doi:10.1016/j.soi.2026.100283
Making AI Agents Practical in Health Professions Education: An Implementation Framework (Preprint)Preprint
Rejeleene, R., & Mehta, N. (2026) · doi:10.2196/preprints.108871
Sayyeda, M., Montasir, P., Kadir, A. K. M. S., Islam, M. T., Moomu, M. A., Rahman, J., Shemanto, M. U., Khondakar, M. J., Akhter, R., & Tina, T. J. (2026) · Springer eBooks · doi:10.1007/978-3-032-23511-4_3
AI ethics practices in Swiss health organisations
Lee, H., Kijewski, S., Ferretti, A., Blasimme, A., & Vayena, E. (2026) · AI and Ethics · doi:10.1007/s43681-026-01286-x
“The underrepresentation of ethnic diversity may lead to unequal benefits from these health AI models and potentially harmful effects when using these tools [ 11 ].”
Saberi, K., Abbood, R. S., Al-Taie, S. F., Smerat, A., Abdullayev, M. M., Maksudova, M. K., Hedayatinia, M., Zarei, A., Nourizadeh, M., Ghahari, A., et al. (2026) · Veterinary Medicine and Science · doi:10.1002/vms3.71152
“…emphasize external multi-centre validation, prospective or temporally separated testing, calibration and uncertainty reporting, performance stratification by breed and disease severity and clinically interpretable error analysis (Norori et al. 2021 ; Cross et al. 2024 ; Maciulevičius et al. 2025 ).”
Ilic, A., Juvet, L. K., Cairns, P., Thornton, K. E. T., & Lie, H. C. (2026) · JMIR mhealth and uhealth · doi:10.2196/94793
“For example, NLP or large language model– based systems that classify patient input or triage symptoms can introduce systematic measurement shifts, which could affect clinical decision support [47,48].”
Innovations using digital technologies for periodontal diagnosis and prognosis: a narrative review
Liedtke, N. B., & Damgaard, C. (2026) · Acta Odontologica Scandinavica · doi:10.2340/aos.v85.46561
“Existing consensus-based reporting standards for AI studies in dentistry already provide a practical framework that periodontal research could adopt to make bias and equity considerations explicit [23, 55].”
InfluentialIntegrating AI-Augmented Practice Into Physical Therapy Education: A Competency Overlay Framework
Hardwick, D. (2026) · Journal of Physical Therapy Education · doi:10.1097/jte.0000000000000497
Yin, Y., Ningyang, G., Gao, K., Wei, Y., Zhou, W., Zhang, Y., Luan, Y., Lina, Z., Liu, F., & Fan, T. (2026) · Materials Today Communications · doi:10.1016/j.mtcomm.2026.115915
Contemporary Approaches in Oral and Maxillofacial Imaging and Diagnosis
Eninanç, İ., ATAPEK, M. M., Ova, U. A., Zengin, U., Ketenci, F., Ozsoy, S. C., Erdoğan, B., Ertürk, M., Aslan, F., Mican, M. M., et al. (2026) · Akademisyen Kitabevi eBooks · doi:10.37609/akya.4040
Strategic Solutions for Overcoming Challenges in AI Adoption
Baig, T., Khan, M. J., & Shehzad, A. (2026) · Springer eBooks · doi:10.1007/978-981-92-0875-3_14
Chiu, H.-Y., Chuang, Y.-T., Zaami, S., & Chen, T.-A. (2026) · Healthcare · doi:10.3390/healthcare14162538
“Rather than eliminating subjectivity, predictive models may inadvertently encode and reproduce existing disparities present in the populations from which they are derived [37,38].”
InfluentialRebollo-Giménez, A. I., Bella, S. L., Matucci‐Cerinic, C., García-Alija, A., Gattorno, M., Alongi, A., & Ruperto, N. (2026) · Current Opinion in Immunology · doi:10.1016/j.coi.2026.102835
AI Ethics in the Physical Sciences: Transparency, Bias, and the Transformation of Discovery
Weatherwax, A. T., & Weatherwax, E. T. (2026) · Springer eBooks · doi:10.1007/978-3-032-12201-8_28
Illamperuma, I., Gandhi, B., Offman, R., & Rosenberg, M. (2026) · JAMIA Open · doi:10.1093/jamiaopen/ooag138
O’Donoghue, M., Weber, S., Hahn, P., Bock, M., & Lautenbach, M. (2026) · Handchirurgie · Mikrochirurgie · Plastische Chirurgie · doi:10.1055/a-2920-9458
Kashif, M., Fatima, A., Shah, M. S., Ahmad, S., & Maqbool, A. (2026) · Qlantic journal of social sciences. · doi:10.55737/qjss.vii-iv.26580
İnan, M., İnan, S. A., Bumın, G., & Aypak, C. (2026) · Seminars in Oncology Nursing · doi:10.1016/j.soncn.2026.152304
(2026) · International Journal of Progressive Research in Engineering Management and Science · doi:10.58257/ijprems54573
Budimir, L. A., Gong, M. A., Quinney, A. F., Matovinovic, I. Z., Zhou, Y., Keane, P. A., Lončarić, S., & Šarunic, M. V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.15195
“Since medical data are difficult to share across institutions, resulting models may underperform for underrepresented populations, diseases, imaging devices, and clinical sites [4].”
Operationalising Inclusion for Participatory Design: Worked Examples for TRIPOD+AI & PROBAST+AI
Martens, R., Bakunda, L., Mushayandebvu, T., & Marshall, Z. (2026) · Health Services Insights · doi:10.1177/11786329261477136
Metadata
- Authors
- Cross, J. L., Choma, M. A., & Onofrey, J. A.
- Affiliations
- Yale University (US)
- Corresponding author
- Cross, James L.
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2024-11-07
- Volume
- 3
- Issue
- 11
- Pages
- e0000651
- ISSN
- 2767-3170 (ISSN-L)
- PMC
- PMC11542778
- OpenAlex
- W4404134492
- Cited by
- 607
- References
- 120
- Citations by year
- 2026: 382 · 2025: 222 · 2024: 3
- FWCI
- 13.83
- 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)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- algorithmic bias, artificial intelligence in healthcare, clinical decision-making, health care disparities, biased training data, missing data, label bias, model evaluation, bias mitigation, model interpretability, social determinants of health, clinical validation
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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.