The DOI matches its Crossref record; 144 of the 164 references it cites were found in a registry or an index; none of the 74 sources its claims cite is checked for support yet.
Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects
Open accessAbstract
Although artificial intelligence (AI) methods hold promise for medical imaging-based prediction tasks, their integration into medical practice may present a double-edged sword due to bias (i.e., systematic errors). AI algorithms have the potential to mitigate cognitive biases in human interpretation, but extensive research has highlighted the tendency of AI systems to internalize biases within their model. This fact, whether intentional or not, may ultimately lead to unintentional consequences in the clinical setting, potentially compromising patient outcomes. This concern is particularly important in medical imaging, where AI has been more progressively and widely embraced than any other medical field. A comprehensive understanding of bias at each stage of the AI pipeline is therefore essential to contribute to developing AI solutions that are not only less biased but also widely applicable. This international collaborative review effort aims to increase awareness within the medical imaging community about the importance of proactively identifying and addressing AI bias to prevent its negative consequences from being realized later. The authors began with the fundamentals of bias by explaining its different definitions and delineating various potential sources. Strategies for detecting and identifying bias were then outlined, followed by a review of techniques for its avoidance and mitigation. Moreover, ethical dimensions, challenges encountered, and prospects were discussed.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This international collaborative review explains bias in medical imaging artificial intelligence across the full pipeline, from definitions and sources to detection, avoidance, mitigation, ethics, challenges, and prospects. It argues that proactive identification and mitigation are needed, while acknowledging that completely bias-free systems are unrealistic.
Key findings
- Bias is framed as systematic error or distance between prediction and truth, with sources spanning study design/dataset, modeling, and deployment, including demographic imbalance, covariate shift, annotation/reference standard bias, data leakage, deployment bias, concept drift, automation bias, and algorithmic aversion.
- Detection strategies include dataset evaluation, unsupervised analysis, subgroup statistical comparison, visualization, independent code review, testing on unseen populations, and explainability analysis; named tools include PROBAST with four bias categories, QUADAS-2 with 14 questions, the under-development PROBAST-AI, TRIPOD-AI, FUTURE-AI, CLEAR, and METRICS.
- Mitigation is divided into preprocessing, during-training, and post-processing approaches; explainable AI methods include perturbation-based methods such as occlusion, LIME, and SHAP, and backpropagation-based methods such as saliency maps and CAM/Grad-CAM.
- Ethical and regulatory discussion cites the WHO’s six key ethical principles for AI in healthcare and the European Union’s AI Act, including Article 10 data governance for high-risk systems and Article 61 post-market surveillance, with full effect in 2026; challenges include limited benchmark diversity and the finding that fewer than approximately 6% of published radiology AI articles partially or completely share experimental data.
Methods
- Design: international collaborative narrative review covering fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects, explicitly without detailed technical discussion.
- Data or sample: no original dataset or systematic search is described; the paper synthesizes prior literature and references, with figures, tables, and collective recommendations in Table 3.
- Main analysis: conceptual and descriptive synthesis; no quantitative meta-analysis or primary statistical analysis is reported.
Limitations
- Stated: the review does not provide a detailed technical discussion; the authors state that expecting completely bias-free systems may be unrealistic and that complete inclusivity of all data types and sources remains unattainable.
- Stated challenges: ambiguities in interpreting results, limited diversity in benchmark datasets, subjectivity in detecting bias, and constraints related to data sharing and patient privacy.
- Evident: as a narrative review, no systematic search strategy, inclusion criteria, or quantitative synthesis is reported in the text; recommendations are expert-based rather than empirically tested here.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
58 Not checked yet · 22 No basis given · 13 Own interpretation · 6 Sources not found · 1 Own result
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Another aspect to carefully consider is the choice of metrics used to estimate the model’s performance, which could introduce bias if those selected do not match the information needed.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to modeling
hedgedconditional- 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.
In the paper
“Additionally, the choice of data preprocessing techniques, such as normalization, augmentation, or cropping, can also influence the model’s output by emphasizing certain features over others.28”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [28] Tajbakhsh N Jeyaseelan L Li Q Chiang JN Wu Z Ding X Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med Image Anal 2020 63 101693 10.1016/j.media.2020.101693 32289663 source
plaindirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Additionally, improper utilization by end-users can also arise when utilizing systems to analyze images from anatomical districts or imaging modalities that differ from those they have been trained and validated with-for example, employing abdominal computed tomography images instead of abdominal magnetic resonance images.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
plaindirect- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Such variations can cause AI systems to become overfitted to the characteristics specific to the data they were trained on, reducing their generalizability and effectiveness when deployed in different settings.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
plaindirect- 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.
In the paper
“In medical imaging, this bias can manifest when an algorithm designed for segmentation tasks is utilized by human operators, whether intentionally or inadvertently, as a detection tool instead.37”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [37] Ueda D Kakinuma T Fujita S et al Fairness of artificial intelligence in healthcare: review and recommendations. Jpn J Radiol 2024 42 1 3 15 37540463 PMC10764412 source
plainconditional- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If these factors are not adequately considered during dataset collection and AI model training, the resulting models may not only perpetuate but also amplify existing disparities.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
hedgedconditional- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“AI in medical imaging is at risk of being compromised by several types of biases, which could adversely affect patient outcomes.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Main points
hedgedconditional- 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: unclear — It is unclear why the paper says it holds.
In the paper
“Bias in the dataset collection and preparation phases can significantly affect the outcomes of AI systems, particularly in the critical domain of medical imaging.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not matchedcites [23] Chen P Wu L Wang L AI fairness in data management and analytics: a review on challenges, methodologies and applications. Appl Sci 2023 13 18 10258
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- 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.
- Not matched
In the paper
“Different reference standards are often available to confirm radiological diagnosis, which may also lead to systematic errors.26”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [26] van der Pol CB McInnes MDF Salameh JP et al Impact of reference standard on CT, MRI, and contrast-enhanced US LI-RADS diagnosis of hepatocellular carcinoma: a meta-analysis. Radiology 2022 303 3 544 545 10.1148/radiol.212340 35230186 source
hedgedconditional- 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.
In the paper
“A broader concept than annotation bias is reference standard bias, affecting the way instances are labeled and consequently impacting algorithm development.25”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [25] Jayakumar S Sounderajah V Normahani P et al Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study. NPJ Digit Med 2022 5 1 11 10.1038/s41746-021-00544-y 35087178 PMC8795185 source
plaindirect- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This fact, whether intentional or not, may ultimately lead to unintentional consequences in the clinical setting, potentially compromising patient outcomes.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Abstract
hedgedconditional- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Bias can be introduced if the images come from a limited number of institutions or geographic locations, as different places may use varying equipment, protocols, and standards for image capture.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
plainconditional- 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.
In the paper
“It should also be considered that, since humans are developing AI models, the latter can also inherit cognitive bias from the former.3”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to modeling
What the sources say
- Not checked yetcites [3] Busby LP, Courtier JL, Glastonbury CM. Bias in radiology: the how and why of misses and misinterpretations.Radiographics.;38(1):236-247. PMC5790309 29194009 source
plaindirect- 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.
In the paper
“Any flaw in these essential starting points inevitably generates a bias in the subsequent steps, such as the selection of training datasets, AI model development, and/or deployment.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [22] Koçak B Cuocolo R dos Santos DP Stanzione A Ugga L Must-have qualities of clinical research on artificial intelligence and machine learning. Balkan Med J 2023 40 1 3 12 10.4274/balkanmedj.galenos.2022.2022-11-51 36578657 PMC9874249 source
boosteddirect- 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.
In the paper
“This bias can stem from a variety of sources and can lead to disparities in the performance of AI systems across different patient groups, potentially exacerbating existing health inequalities.23”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not matchedcites [23] Chen P Wu L Wang L AI fairness in data management and analytics: a review on challenges, methodologies and applications. Appl Sci 2023 13 18 10258
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- 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.
- Not matched
None of the sources cited for this claim have been checked yet.
In the paper
“In recent years, the technical evolution of ML models, and especially the rise of large neural network architectures, has begun to challenge the traditional approach of validation (or cross-validation) error minimization as the ideal strategy to optimize the bias-variance tradeoff during model training.17, 18, 19, 20”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Definition of bias in artificial intelligence
What the sources say
- Not checked yetcites [17] Guan X Burton H Bias-variance tradeoff in machine learning: theoretical formulation and implications to structural engineering applications. Structures 2022 46 17 30 10.1016/j.istruc.2022.10.004 source
- Not matchedcites [18] Bouchard G Bias-variance tradeoff in hybrid generative-discriminative models. In:Sixth International Conference on Machine Learning and Applications (ICMLA 2007). Cincinnati, OH, USA. 2007 124 129
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [19] Rocks JW Mehta P Memorizing without overfitting: bias, variance, and interpolation in overparameterized models. Phys Rev Res 2022 4 1 013201 36713351 PMC9879296 source
plaindirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Moreover, if a small group of experts annotates the dataset, their individual biases and level of expertise can influence the labels, affecting the AI model’s learning process.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
plaindirect- 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.
In the paper
“For example, if a dataset predominantly consists of images from a particular racial or ethnic group, the AI model trained on this dataset may exhibit reduced accuracy when applied to individuals from other groups.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [24] Larrazabal AJ Nieto N Peterson V Milone DH Ferrante E Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc Natl Acad Sci U S A 2020 117 23 12592 12594 10.1073/pnas.1919012117 32457147 PMC7293650 source
hedgeddirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An example of data leak in medical imaging is represented by the inclusion of different scans from the same patient both in the training and validation dataset, which increases the risk of overfitting.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to modeling
plaindirect- 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.
In the paper
“Similar issues arise with gender, age, and socio-economic status, where AI systems may perform better for the demographic groups that are overrepresented in the training data (Figure 4).24”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [24] Larrazabal AJ Nieto N Peterson V Milone DH Ferrante E Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc Natl Acad Sci U S A 2020 117 23 12592 12594 10.1073/pnas.1919012117 32457147 PMC7293650 source
hedgedconditional- 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.
In the paper
“Bias can emerge when taking the very first step into the development of AI solutions for medical imaging, which is the correct identification of an unmet and relevant clinical need.21”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not matchedcites [21] Gong J, Currano RM, Sirkin D, Yeung S, Holsinger FC. NICE: Four Human-Centered AI principles for bridging the AI-to-clinic translational gap. In: 2021. Accessed April 8, 2024.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- 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.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Moreover, bias can stem from broader historical and societal inequities that are reflected in the data.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
plaindirect- 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.
In the paper
“In this context, a common and serious source of bias in model validation lies in data leakage.31”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to modeling
What the sources say
- Not checked yetcites [31] Kapoor S Narayanan A Leakage and the reproducibility crisis in machine-learning-based science. Patterns (N Y) 2023 4 9 100804 10.1016/j.patter.2023.100804 37720327 PMC10499856 source
plaindirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The process of labeling medical images, which is often performed by human experts, can lead to inconsistencies due to subjective interpretation of what the images represent and in turn to annotation bias.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
plaindirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Therefore, potential bias present in any of the algorithms will propagate down the pipeline and be inherited by the final model or even amplified in it, resulting in propagation bias.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to modeling
plaindirect- 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.
In the paper
“Statistical comparison of model output according to different patient groups or confounders that may exist in the training dataset, such as the gender or age of patients. Potential discrepancies in group results could indicate a source of bias that can affect the final results.48”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [48] Gichoya JW Thomas K Celi LA et al AI pitfalls and what not to do: mitigating bias in AI. Br J Radiol 2023 96 1150 20230023 37698583 PMC10546443 source
hedgedconditional- 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.
In the paper
“These post-processing methods can be used in black-box settings, similar to preprocessing methods, as they do not require access to model parameters.76”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [76] Feldman T, Peake A. End-to-end bias mitigation: removing gender bias in deep learning. Published online June 20, 2021. source
plaindirect- 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.
In the paper
“Finally, another set of methods mitigates bias in a post-processing phase after model training by changing prediction based on fairness constraints.76”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [76] Feldman T, Peake A. End-to-end bias mitigation: removing gender bias in deep learning. Published online June 20, 2021. source
plaindirect- 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.
None of the sources cited for this claim have been checked yet.
In the paper
“AI systems may transport various types of bias stemming from their underlying training data.68, 69”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [68] Gallegos IO, Rossi RA, Barrow J, et al. Bias and Fairness in large language models: a survey. Published online 2023. source
- Not checked yetcites [69] Mehrabi N Morstatter F Saxena N Lerman K Galstyan A A Survey on bias and fairness in machine learning. ACM Comput Surv 2022 54 6 1 35 10.1145/3457607 source
hedgedconditional- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Nonetheless, even data collected following these principles may still reflect existing structural and historical biases.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
plainconditional- 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: unclear — It is unclear why the paper says it holds.
In the paper
“One of the first strategies that can be used to identify bias related to the dataset is dataset evaluation against a set of predefined criteria (searching for exclusion bias, selection bias, recall bias, observer bias, and prejudice bias) and comprehensive data analysis.47”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [47] Rouzrokh P Khosravi B Faghani S et al Mitigating bias in radiology machine learning: 1. data handling. Radiol Artif Intell 2022 4 5 e210290 36204544 PMC9533091 source
plaindirect- 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.
None of the sources cited for this claim have been checked yet.
In the paper
“Generative AI models, such as large language models or vision-language models capable of synthesizing images, additionally allow for tailored data augmentation by creating new examples that meet a set of targeted criteria.71, 72, 73”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [71] Carrillo-Perez F, Pizurica M, Zheng Y, et al. Generation of synthetic whole-slide image tiles of tumours from RNA-sequencing data via cascaded diffusion models.Nat Biomed Eng 2024 38514775 source
- Not checked yetcites [72] Chambon P, Bluethgen C, Delbrouck JB, et al. RoentGen: Vision-language foundation model for chest X-ray generation. Published online 2022. PMC11861387 39187663 source
- Not checked yetcites [73] Wiles O, Albuquerque I, Rebuffi SA, et al. Generative models improve fairness of medical classifiers under distribution shifts. Published online May 31, 2023. PMC11031395 38600282 source
plaindirect- 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.
In the paper
“For systematic reviews of AI studies, the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) has been widely used to detect the risk of bias.62”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [62] Whiting PF Rutjes AW Westwood ME et al QUADAS-2: A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies. Ann Intern Med 2011 155 8 529 536 22007046
boosted- 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.
In the paper
“Other techniques, such as pruning, aiming to compress the model may also disproportionately impact underrepresented subsets in the data.74”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not matchedcites [74] Hooker S, Moorosi N, Clark G, Bengio S, Denton E. Characterising bias in compressed models. Published online 2020.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- 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.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A classic example is optimizing a model for overall accuracy, which may severely impact the model performance on minority class samples in imbalanced setups.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
hedgedconditional- 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.
In the paper
“These methods help us discern if confounders or biases are present in the model, allowing for their control or removal.107”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [107] Borys K Schmitt YA Nauta M et al Explainable AI in medical imaging: an overview for clinical practitioners - Beyond saliency-based XAI approaches. Eur J Radiol 2023 162 110786 36990051 source
plaindirect- 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.
In the paper
“In the context of AI in medical imaging, automation bias can manifest when clinicians or radiologists place undue trust in the outputs or recommendations provided by AI algorithms, leading them to overlook potentially important information or make errors in diagnosis or treatment planning.43”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [43] Bitterman DS Aerts HJWL Mak RH Approaching autonomy in medical artificial intelligence. Lancet Digit Health 2020 2 9 e447 e449 10.1016/S2589-7500(20)30187-4 33328110 source
plaindirect- 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.
In the paper
“Nonetheless, human observer decisions relying on AI/ML model outputs and their reported uncertainty may be unduly swayed by the uncertainties inherent in the model’s output.41”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not matchedcites [41] Hüllermeier E Waegeman W Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach Learn 2021 110 3 457 506
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- 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.
- Not matched
In the paper
“Automation bias can occur in busy clinical settings where clinicians may feel pressure to make rapid decisions, leading them to rely on AI-generated results as a shortcut rather than engaging in thorough analysis.44”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [44] Goddard K Roudsari A Wyatt JC Automation bias: a systematic review of frequency, effect mediators, and mitigators. J Am Med Inform Assoc 2012 19 1 121 127 21685142 PMC3240751 source
plaindirect- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Consequently, humans may place greater importance on a prediction that exhibits high certainty, even if it happens to be incorrect, compared with one with lower certainty that is actually correct.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
hedgedconditional- 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.
In the paper
“Nonetheless, the current version of PROBAST is not suitable for the evaluation of ML studies, and this is the reason that the PROBAST group has initiated the process of developing an AI-specific version of PROBAST called PROBAST-AI, which is still under development.61”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [61] Collins GS Dhiman P Andaur Navarro CL et al Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open 2021 11 7 e048008 10.1136/bmjopen-2020-048008 PMC8273461 34244270 source
plain- 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.
In the paper
“A lack of adequate training or education on how to effectively integrate AI algorithms into workflow may favor automation bias.45”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [45] Dratsch T Chen X Rezazade Mehrizi M et al Automation Bias in Mammography: The impact of artificial intelligence BI-RADS suggestions on reader performance. Radiology 2023 307 4 e222176 10.1148/radiol.222176 37129490 source
hedgedconditional- 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.
In the paper
“This can occur when some diseases or events are collected with underrepresentation or overrepresentation compared with their prevalence in the general population or clinical practice due to the limited patient diversity included in the training data; this causes a class imbalance due to an uneven distribution between the training data and the actual population to which the AI model is applied.120”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [120] Tejani AS Ng YS Xi Y Rayan JC Understanding and Mitigating bias in imaging artificial intelligence. Radiographics 2024 44 5 e230067 10.1148/rg.230067 38635456 source
plaindirect- 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.
In the paper
“Currently, patients can decline being evaluated by AI-based tools according to the right to informed consent for any procedure in the hospital.129”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
What the sources say
- Not checked yetcites [129] Ploug T Holm S The right to a second opinion on artificial intelligence diagnosis—remedying the inadequacy of a risk-based regulation. Bioethics 2023 37 3 303 311 10.1111/bioe.13124 36434807 source
plain- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Multicentric databases can potentially overcome this challenge by collecting a large number of diverse and representative data in rarer conditions.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
hedgedconditional- 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.
In the paper
“Currently, these publicly available datasets are limited to a narrow spectrum of diseases or countries of origin of the patient population.123”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [123] Tripathi S Gabriel K Dheer S et al Understanding Biases and Disparities in Radiology AI Datasets: a review. J Am Coll Radiol 2023 20 9 836 841 37454752 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.
None of the sources cited for this claim have been checked yet.
In the paper
“As AI tools learn from archival data, a narrowed data source results in AI models that are not generalizable in heterogeneous patient populations with different demographics, clinical characteristics, and disease prevalence, leading to perpetuated bias in the final AI model.120, 121”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [120] Tejani AS Ng YS Xi Y Rayan JC Understanding and Mitigating bias in imaging artificial intelligence. Radiographics 2024 44 5 e230067 10.1148/rg.230067 38635456 source
- Not checked yetcites [121] Flory MN Napel S Tsai EB Artificial intelligence in radiology: opportunities and challenges.Semin Ultrasound CT MRI. Published online February 2024 S0887217124000052 38403128 source
plaindirect- 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.
In the paper
“Finally, data labeling for model training can be affected by the human image interpretation and diagnostic performance of the selected reference standard for the investigated condition.121”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [121] Flory MN Napel S Tsai EB Artificial intelligence in radiology: opportunities and challenges.Semin Ultrasound CT MRI. Published online February 2024 S0887217124000052 38403128 source
plaindirect- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Additionally, it requires rigorous data governance, including bias examination and mitigation measures, to prevent impacts on health, safety, fundamental rights, or unlawful discrimination, particularly when data outputs affect future inputs.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
plaindirect- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The complexity of AI tools makes it difficult to detect.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
plaindirect- 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.
In the paper
“Continuous learning can increase bias if the new data are biased.139”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Prospects
What the sources say
- Not checked yetcites [139] DeCamp M Lindvall C Latent bias and the implementation of artificial intelligence in medicine. J Am Med Inform Assoc 2020 27 12 2020 2023 32574353 PMC7727353 source
plainconditional- 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.
In the paper
“In the current radiological literature, there are ongoing difficulties in sharing benchmark datasets, with fewer than approximately 6% of all published articles in radiology journals partially or completely sharing the experimental data used to build the AI models.125”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [125] Venkatesh K Santomartino SM Sulam J Yi PH Code and data sharing practices in the radiology artificial intelligence literature: a meta-research study. Radiol Artif Intell 2022 4 5 e220081 10.1148/ryai.220081 36204536 PMC9530751 source
plain- 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.
In the paper
“Ambiguities can also originate during the different applications of the AI tools from the intended use statement provided by the AI developers, increasing the risk of off-label or erroneous applications of AI in clinical practice.119”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [119] van Leeuwen KG Hedderich DM Harvey H Schalekamp S How AI should be used in radiology: assessing ambiguity and completeness of intended use statements of commercial AI products. Insights Imaging 2024 15 1 51 10.1186/s13244-024-01616-9 38366046 PMC10873256 source
plaindirect- 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.
In the paper
“These algorithms can ensure equitable outcomes across patient populations.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Prospects
What the sources say
- Not checked yetcites [134] Ferrara C Sellitto G Ferrucci F Palomba F De Lucia A Fairness-aware machine learning engineering: how far are we? Empir Softw Eng? Empir Softw Eng 2023 29 1 9 10.1007/s10664-023-10402-y 38027253 PMC10673752 source
plaindirect- 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.
- Probably not a substantial claim. 39
- It may state two separate claims as one. 14
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Medical publication trends indicate a growing interest in bias in AI (Figure 1).”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Main points
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Some could be highly accurate but also costly and poorly available, whereas others could neglect intermediate findings or be operator-dependent,27 potentially reducing label applicability and reliability.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to study design and dataset
What the sources say
- Not checked yetcites [27] Chen PC Mermel CH Liu Y Evaluation of artificial intelligence on a reference standard based on subjective interpretation. Lancet Digit Health 2021 3 11 e693 e695 10.1016/S2589-7500(21)00216-8 34561202 source
hedgedconditional- 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.
It may state two separate claims as one.
In the paper
“In particular, this bias can lead to skewed data cohorts, incomplete information, heightened uncertainty in outcomes, and potential dismissal of algorithm-assisted medical advice.40”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [40] Olteanu A Castillo C Diaz F Kıcıman E Social data: biases, methodological pitfalls, and ethical boundaries. Front Big Data 2019 2 13 10.3389/fdata.2019.00013 33693336 PMC7931947 source
plaindirect- 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.
It may state two separate claims as one.
In the paper
“Specifically, it arises when the correlation between input variables, such as images, and output predictions, such as diagnoses, evolves due to fluctuations in data, such as variations in image acquisition hardware or protocols, shifts in disease prevalence, or advancements in gold-standard technologies.38”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [38] Roland T Böck C Tschoellitsch T et al Domain shifts in machine learning based Covid-19 diagnosis from blood tests. J Med Syst 2022 46 5 23 35348909 PMC8960704 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The concept of bias in machine learning (ML) research and more generally in the field of predictive modeling is intrinsically tied to the concept of variance.14”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Definition of bias in artificial intelligence
What the sources say
- Not checked yetcites [14] Geman S Bienenstock E Doursat R Neural networks and the bias/variance dilemma. Neural Comput 1992 4 1 1 58 10.1162/neco.1992.4.1.1 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Uncertainty bias encompasses the influence of uncertainty on decision-making stemming from AI/ML models.39”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [39] Drukker K Chen W Gichoya J et al Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment. J Med Imaging(Bellingham) 2023 10 6 061104 10.1117/1.jmi.10.6.061104 37125409 PMC10129875 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“From a mathematical point of view, noise (the joint probability distribution between training and test/inference samples), bias, and variance are the three components that lead to model performance degradation and negatively affect generalization to new data.17”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Definition of bias in artificial intelligence
What the sources say
- Not checked yetcites [17] Guan X Burton H Bias-variance tradeoff in machine learning: theoretical formulation and implications to structural engineering applications. Structures 2022 46 17 30 10.1016/j.istruc.2022.10.004 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Behavioral bias pertains to the potential distortions in user behavior seen across various platforms, contexts, or datasets.39”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [39] Drukker K Chen W Gichoya J et al Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment. J Med Imaging(Bellingham) 2023 10 6 061104 10.1117/1.jmi.10.6.061104 37125409 PMC10129875 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, it should be made clear that these two entities are interdependent, and reducing one (e.g., variance) typically comes at the expense of increasing the other (i.e., bias), which gives birth to the concept of a bias-variance tradeoff.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Definition of bias in artificial intelligence
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“A deployment bias emerges when there is a misalignment between the envisioned purpose of a system or algorithm and its actual application.36”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [36] Rajpurkar P Chen E Banerjee O Topol EJ AI in health and medicine. Nat Med 2022 28 1 31 38 10.1038/s41591-021-01614-0 35058619 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“This starts with a code review that can be carried out by an independent experienced coder/auditor.49”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [49] Murphy-Hill E Jaspan CN Egelman C Cheng L The Pushback effects of race, ethnicity, gender, and age in code review. Commun ACM 2022 65 3 52 57 10.1145/3474097 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Apart from collecting more data, strategies at the data processing stage may include the creation of more representative training datasets by data augmentation (e.g., by specifically adding underrepresented examples to the data through additional sampling or data generation) or data filtering (e.g., actively undersampling or filtering out undesirable or non-representative samples).68”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [68] Gallegos IO, Rossi RA, Barrow J, et al. Bias and Fairness in large language models: a survey. Published online 2023. source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The composition of the involved teams can influence the AI’s propensity for bias.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By incorporating the above-mentioned considerations early into the design phase, developers can create systems that are less likely to perpetuate or amplify biases.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
hedgedconditional- 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.
Probably not a substantial claim.
None of the sources cited for this claim have been checked yet.
In the paper
“The way data are presented to the model during training (affected by the problem formulation and the labeling methodology) and how model parameters are updated (defined through training setup including the objective function) can introduce bias into the model.13, 68”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [13] Obermeyer Z Powers B Vogeli C Mullainathan S Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019 366 6464 447 453 10.1126/science.aax2342 31649194 source
- Not checked yetcites [68] Gallegos IO, Rossi RA, Barrow J, et al. Bias and Fairness in large language models: a survey. Published online 2023. source
plainconditional- 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.
It may state two separate claims as one.
In the paper
“Additionally, algorithms can be categorized according to whether they explicitly or implicitly address bias by accessing or not accessing the bias variables during training.77”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [77] Shrestha R, Kafle K, Kanan C. An investigation of critical issues in bias mitigation techniques. In:IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE; Waikoloa, HI, USA: 2022:2512-2523.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Guiding principles, such as transparency, fairness, non-maleficence, and respect for privacy from the outset, are widely included in recommendations and position papers and can help to prevent bias (Figure 9).67”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [67] Jobin A Ienca M Vayena E The global landscape of AI ethics guidelines. Nat Mach Intell 2019 1 9 389 399
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Additionally, these are independent of the model and can be used in a black-box setting by altering the data distribution to increase model fairness.76”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [76] Feldman T, Peake A. End-to-end bias mitigation: removing gender bias in deep learning. Published online June 20, 2021. source
plaindirect- 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.
It may state two separate claims as one.
In the paper
“Bias mitigation algorithms can be divided into three types according to the phase in which they are applied: in a preprocessing phase, during model training, or after model training.76”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not matchedcites [76] Feldman T, Peake A. End-to-end bias mitigation: removing gender bias in deep learning. Published online June 20, 2021.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim have been checked yet.
In the paper
“Re-sampling and re-weighting algorithms focus on rebalancing the class distribution by adjusting the sample probability/loss weight for majority/minority samples.78, 79, 80, 81, 82, 83”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
What the sources say
- Not checked yetcites [78] Feldman M, Friedler SA, Moeller J, Scheidegger C, Venkatasubramanian S. Certifying and removing disparate impact. In:Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’15. Association for Computing Machinery; 2015:259-268. source
- Not checked yetcites [79] Cui Y, Jia M, Lin TY, Song Y, Belongie S. Class-balanced loss based on effective number of samples. In:IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA: 2019:9260-9269. source
- Not checked yetcites [80] Zou Y, Yu Z, Kumar BVKV, Wang J. Domain adaptation for semantic segmentation via class-balanced self-training. Published online October 25, 2018. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Nonetheless, the current version of PROBAST is not suitable for the evaluation of ML studies, and this is the reason that the PROBAST group has initiated the process of developing an AI-specific version of PROBAST called PROBAST-AI, which is still under development.61”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [61] Collins GS Dhiman P Andaur Navarro CL et al Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open 2021 11 7 e048008 10.1136/bmjopen-2020-048008 PMC8273461 34244270 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Consider this scenario: AI/ML models can be “confidently wrong,” meaning they may yield incorrect outcomes with a high level of certainty.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
hedgedconditional- 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: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“Transparent and comprehensive documentation of the AI system’s design choices, data sources, and any assumptions made during development (e.g., through model cards)75 is crucial and can help spot sources of bias before, during, and after training.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
What the sources say
- Not checked yetcites [75] Mitchell M, Wu S, Zaldivar A, et al. Model cards for model reporting. In:Proceedings of the Conference on Fairness, Accountability, and Transparency. ACM; 2019:220-229.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Teams that are diverse in terms of gender, ethnicity, culture, and professional background bring a wide array of perspectives to the table, which can help identify and eliminate potential biases early in the development process.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Avoidance strategies
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In general, XAI methods can be categorized into two main groups: perturbation-based and backpropagation-based explanations.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Mitigation strategies
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Algorithmic aversion refers to a phenomenon where clinicians or healthcare professionals exhibit reluctance or skepticism toward relying on AI algorithms for making diagnostic or treatment decisions in medical imaging.46”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [46] Cadario R Longoni C Morewedge CK Understanding, explaining, and utilizing medical artificial intelligence. Nat Hum Behav 2021 5 12 1636 1642 34183800 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Reporting guidelines, such as the Fairness Universality Traceability Usability Robustness Explainability-AI and TRIPOD-AI, can assist authors of AI manuscripts in reporting their studies according to the Fairness principle, promoting the identification of bias sources.58, 63, 64”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias detection/identification
What the sources say
- Not checked yetcites [58] Klontzas ME Gatti AA Tejani AS Kahn CE Jr AI reporting guidelines: how to select the best one for your research. Radiol Artif Intell 2023 5 3 e230055 10.1148/ryai.230055 37293341 PMC10245184 source
- Not matchedcites [63] Lekadir K, Osuala R, Gallin C, et al. FUTURE-AI: Guiding principles and consensus recommendations for trustworthy artificial intelligence in medical imaging. Published online October 30, 2023.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [64] Collins GS Moons KGM Dhiman P et al TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 2024 385 7996 e078378 10.1038/d41586-024-00173-x 38626948 PMC11019967 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, there are several challenges in handling bias that can be related to ambiguities in interpreting results, limited diversity in benchmark datasets, and the subjectivity of detecting bias.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Automation bias refers to the tendency of individuals to rely excessively on automated systems, such as AI algorithms, and to disregard or underutilize their own judgment or critical thinking skills.42”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Bias related to deployment
What the sources say
- Not checked yetcites [42] Khera R Simon MA Ross JS Automation Bias and Assistive AI: Risk of Harm From AI-driven clinical decision support. JAMA 2023 330 23 2255 2257 10.1001/jama.2023.22557 38112824 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By identifying and addressing biases, these systems can improve healthcare outcomes and equity.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Prospects
plaindirect- 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.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Understanding that medical imaging AI systems are sensitive to biases is key for their effective real-world integration into clinical practice.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Final remarks
plaincorrelational- 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: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Before going into detail, it should be acknowledged that expecting completely bias-free systems may be unrealistic.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Prospects
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Despite the aspiration for unbiased AI, complete inclusivity of all data types and sources remains an unattainable goal in model development.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Final remarks
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Concerning monitoring, Article 61 of the legislation mandates that developers of high-risk AI systems establish ongoing, systematic post-market surveillance mechanisms.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Additionally, the lack of diversity among developers and researchers can worsen these issues, as teams may unconsciously favor perspectives similar to their own.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Subjectivity in the detection of bias can be related to personal interpretation and individual perspectives related to the identification of the bias itself.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Article 10 mandates that for high-risk AI systems, training, validation, and testing datasets must be relevant, representative, error-minimal, and complete for their intended use.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The recent European Union’s AI Act serves as a pioneering legal framework aimed at regulating AI use, particularly in high-risk applications such as healthcare (as defined in Article 6).”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, AI software trained for adult fracture detection is at risk of erroneous results if applied in a pediatric population.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Publicly accessible benchmarks are essential for comparison for AI models and represent a crucial element of open science.122”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [122] Bell LC Shimron E Sharing Data Is Essential for the Future of AI in Medical Imaging. Radiol Artif Intell 2024 6 1 e230337 10.1148/ryai.230337 38231036 PMC10831510 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“However, although sharing data is essential for developing robust AI tools, patient privacy when collecting medical information can pose significant challenges.124”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [124] Ferrara E Fairness and bias in artificial intelligence: a brief survey of sources, impacts, and mitigation strategies. Sci 2023 6 1 3 10.3390/sci6010003 source
plainconditional- 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.
It may state two separate claims as one.
In the paper
“The 2020 Dutch case against the “system risk indication” tool, which violated privacy laws and wrongly identified innocent people as fraud suspects, underscores the impact of such biases.128”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
What the sources say
- Not checked yetcites [128] SyRI legislation in breach of European Convention on Human Rights. Accessed April 11, 2024.
plaindirect- 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.
It may state two separate claims as one.
In the paper
“Moreover, different sources of bias can contribute to the generation of bias, including the data source, algorithm, and users, which makes the identification more cumbersome.124”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Potential challenges
What the sources say
- Not checked yetcites [124] Ferrara E Fairness and bias in artificial intelligence: a brief survey of sources, impacts, and mitigation strategies. Sci 2023 6 1 3 10.3390/sci6010003 source
plaindirect- 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.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Set to fully take effect in 2026, the act governs the development, deployment, and use of AI, ensuring safety, transparency, and adherence to ethical standards across the EU.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The WHO principles 2 and 5 address bias, mandating that AI tools prioritize human well-being, safety, and public interest.”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
What the sources say
- Not checked yetcites [127] Ethics and Governance of Artificial Intelligence for Health: WHO guidance. Published online 2021.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The World Health Organization (WHO) poses six key ethical principles for AI in healthcare in their framework (Figure 9): (1) protect autonomy, (2) promote human well-being, human safety, and the public interest, (3) ensure transparency, explainability, and intelligibility, (4) foster responsibility and accountability, (5) ensure inclusiveness and equity, and (6) promote AI that is responsive and s”
§ Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects > Ethical considerations
What the sources say
- Not checked yetcites [127] Ethics and Governance of Artificial Intelligence for Health: WHO guidance. Published online 2021.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper relies on this without support.
AI has been more progressively and widely embraced in medical imaging than in any other medical field.
“This concern is particularly important in medical imaging, where AI has been more progressively and widely embraced than any other medical field.”
The paper relies on this without support.
The general sources and types of bias in machine learning apply to medical imaging AI.
“This section focuses on the most common sources of bias that medical imaging professionals, particularly radiologists, may encounter.”
The authors state this as an assumption.
AI models are biased.
“Even though AI models are assumed to be biased, AI-based bias auditing tools may be leveraged to help mitigate bias.132, 133”
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?
In the citing paper
“Incorrect estimation can lead to misinformed decisions, compromising patient safety and treatment efficacy32,33.”
From Probabilistic medical predictions of large language models (2024) · cites this paper as [32]
Citations
Cites
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
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies
Whiting, P. F., Rutjes, A. W. S., Westwood, M. E., Mallett, S., Deeks, J. J., Reitsma, J. B., Leeflang, M. M. G., Sterne, J. A. C., Bossuyt, P. M. M., & the QUADAS-2 Group* (2011) · Annals of Internal Medicine · doi:10.7326/0003-4819-155-8-201110180-00009 · Cited by 14,199 · cited 1×
“62 The QUADAS-2 tool includes 14 questions and provides an estimate of the risk of bias in the study, categorizing it as high, low, or unclear.”
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
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×
“13,68 A classic example is optimizing a model for overall accuracy, which may severely impact the model performance on minority class samples in imbalanced setups.”
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909 · cited 1×
“116-118”
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
The global landscape of AI ethics guidelines
Jobin, A., Ienca, M., & Vayena, E. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0088-2 · Cited by 6,220 · cited 1×
“67 Transparency increases explainability, interpretability, and similar acts of communication and disclosure, which in the context of bias mitigation applies to the explicit, proactive thought about which training data are used, and how they are collected, processed, and employed.”
Research works printed but not linked: 11
- 21. Gong J, Currano RM, Sirkin D, Yeung S, Holsinger FC. NICE: Four Human-Centered AI principles for bridging the AI-to-clinic translational gap. In: 2021. Accessed April 8, 2024. [CrossRef]
- 74. Hooker S, Moorosi N, Clark G, Bengio S, Denton E. Characterising bias in compressed models. Published online 2020. [CrossRef]
- Waikoloa, HI, USA: 2022:2512-2523. [CrossRef]
- 92. Ramakrishnan S, Agrawal A, Lee S. Overcoming language priors in visual question answering with adversarial regularization. Published online November 8, 2018. [CrossRef]
- 96. Arjovsky M, Bottou L, Gulrajani I, Lopez-Paz D. Invariant risk minimization. Published online March 27, 2020. [CrossRef]
- 101. Pezeshki M, Kaba SO, Bengio Y, Courville A, Precup D, Lajoie G. Gradient starvation: a learning proclivity in neural networks. Published online November 24, 2021. [CrossRef]
- 106. Lohia PK, Ramamurthy KN, Bhide M, Saha D, Varshney KR, Puri R. Bias mitigation post-processing for individual and group fairness. Published online December 14, 2018. [CrossRef]
- 108. Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. Published online November 28, 2013. [CrossRef]
- 112. Dabkowski P, Gal Y. Real time image saliency for black box classifiers. Published online May 22, 2017. [CrossRef]
- 127. Ethics and Governance of Artificial Intelligence for Health: WHO guidance. Published online 2021. [CrossRef]
- 128. SyRI legislation in breach of European Convention on Human Rights. Accessed April 11, 2024. [CrossRef]
Cited by
Sorted by citations
Bias 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
“While some reviews concentrate on a single medical domain, particularly in medical imaging [23,24], our discussions integrate real-world examples across diverse medical domains, enabling unique analysis of cross-domain challenges and broader systemic issues, such as biases in funding and…”
BackgroundOgut, E. (2025) · Clinics and Practice · doi:10.3390/clinpract15090169 · Cited by 107
“Otherwise, AI could inadvertently perpetuate or exacerbate healthcare disparities [43].”
Simon, B. D., Ozyoruk, K. B., Gelikman, D. G., Harmon, S. A., & Türkbey, B. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242631 · Cited by 73
“With evidence that multimodal AI may be more accurate for some AI applications 27,59-69, 80 , 93 and that multimodal Considering the dynamic medical environment and its quickly changing technology and guidelines, AI and the data on which it is trained will have to change as quickly as the clinic.”
BackgroundRadiology AI and sustainability paradox: environmental, economic, and social dimensions
Koçak, B., Ponsiglione, A., Romeo, V., Ugga, L., Huisman, M., & Cuocolo, R. (2025) · Insights into Imaging · doi:10.1186/s13244-025-01962-2 · Cited by 61
Self-citationProbabilistic medical predictions of large language models
Gu, B., Desai, R. J., Lin, K. J., & Yang, J. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01366-4 · Cited by 50
Metadata
- Authors
- Koçak, B., Ponsiglione, A., Stanzione, A., Bluethgen, C., Santinha, J., Ugga, L., Huisman, M., Klontzas, M. E., Cannella, R., & Cuocolo, R.
- Affiliations
- Sağlık Bilimleri Üniversitesi (TR)
- University of Naples Federico II (IT)
- Champalimaud Foundation (PT)
- Radboud University Medical Center (NL)
- University of Crete (GR)
- University of Palermo (IT)
- University of Salerno (IT)
- Corresponding author
- Koçak, Burak
- ORCID
- Venue
- Diagnostic and Interventional Radiology
- Publisher
- Galenos Yayinevi
- Published
- 2024-07-02
- Volume
- 31
- Issue
- 2
- Pages
- 75-88
- ISSN
- 1300-4360 (ISSN-L)
- 1305-3825
- 1305-3612
- PMC
- PMC11880872
- OpenAlex
- W4400252889
- Semantic Scholar
- a42554ce8fc8a3c3b6235abac522bc2a27158281
- Cited by
- 168
- References
- 164
- Citations by year
- 2026: 66 · 2025: 93 · 2024: 9
- FWCI
- 3.83
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by-nc
- Locations
- Diagnostic and Interventional Radiology (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, cc-by-nc)
- Radboud Repository (Radboud University) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Archivio Istituzionale della Ricerca - Università degli Studi della Campania "Luigi Vanvitelli" (submittedVersion)
- Nova Science Publishers (Nova Science Publishers, Inc.) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, cc-by-nc)
- Zurich Open Repository and Archive (University of Zurich)
- 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, diagnostic imaging, bias detection, bias mitigation, bias avoidance, ethical implications of AI, clinical implementation of AI, patient outcomes
- MeSH terms
- Algorithms, Artificial Intelligence, Diagnostic Imaging, Humans, Bias
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.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
