The DOI matches its Crossref record; 72 of the 78 references it cites were found in a registry or an index; none of the 20 sources its claims cite is checked for support yet.
Explainable Artificial Intelligence (XAI): Concepts and Challenges in Healthcare
Open accessPublished version of a preprint
Abstract
Artificial Intelligence (AI) describes computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and language translation. Examples of AI techniques are machine learning, neural networks, and deep learning. AI can be applied in many different areas, such as econometrics, biometry, e-commerce, and the automotive industry. In recent years, AI has found its way into healthcare as well, helping doctors make better decisions (“clinical decision support”), localizing tumors in magnetic resonance images, reading and analyzing reports written by radiologists and pathologists, and much more. However, AI has one big risk: it can be perceived as a “black box”, limiting trust in its reliability, which is a very big issue in an area in which a decision can mean life or death. As a result, the term Explainable Artificial Intelligence (XAI) has been gaining momentum. XAI tries to ensure that AI algorithms (and the resulting decisions) can be understood by humans. In this narrative review, we will have a look at some central concepts in XAI, describe several challenges around XAI in healthcare, and discuss whether it can really help healthcare to advance, for example, by increasing understanding and trust. Finally, alternatives to increase trust in AI are discussed, as well as future research possibilities in the area of XAI.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This narrative review surveys the current status of Explainable Artificial Intelligence (XAI) in healthcare, covering the "black box" trust problem, legal/regulatory drivers, transparent versus post-hoc explainability, privacy and security trade-offs, and the tension between explainability and accuracy. The author argues that in healthcare accuracy may outweigh explainability, and that trust might better be built through robustness, fairness, reproducibility, and human–AI collaboration than through explanation alone.
Key findings
- XAI is growing rapidly in the literature: the first mention of "explainable artificial intelligence" in a PubMed title, abstract or keyword was in 2018, and it has since been mentioned 511 times, of which more than half (310) appeared in 2022 or the first months of 2023; Embase shows a similar trend (queries performed 2023-03-06).
- Explainability and accuracy can trade off: making a model fully transparent (a "glass box") may require simplification that reduces the accuracy of a highly predictive model (a "crystal ball"). Van der Veer et al. concluded citizens may value explainability in healthcare less than in non-healthcare domains and less than professionals assume, especially weighed against accuracy.
- XAI is double-edged for privacy and security: it can help detect errors and malicious behavior, but explanations may reveal sensitive information or enable manipulation via reverse engineering. Saifullah et al. recommend differential private federated learning plus perturbation-based XAI methods when both privacy and explainability are required.
- Explanations do not automatically produce trust: Le Merrer and Trédan show remote explainability cannot prevent a service provider from lying about the true reasons for its decisions, while Druce et al. found a statistically significant increase in user trust and acceptance using a three-fold explanation.
Methods
- Design: narrative review of XAI concepts, issues, and challenges in healthcare, with no systematic review protocol described.
- Data: no new data were created or analyzed; the paper draws on cited literature and a bibliometric query of PubMed and Embase for the term "explainable artificial intelligence" in titles, abstracts and keywords, performed on 2023-03-06.
- Analysis: thematic discussion organized into sections covering transparency, legal/regulatory compliance (GDPR, the EU AI Act, HIPAA, PIPL), transparent vs. post-hoc explainability, privacy/security, human–AI collaboration, trust, scientific XAI (sXAI), the explainability–accuracy balance, measurement of explainability, and future complexity.
Limitations
- The paper states no formal limitations section; it is explicitly a narrative review, and the text notes that explainability is difficult to measure because "the quality of an explanation is somewhat subjective."
- Evident from the text: the review is a non-systematic narrative synthesis by a single author, so selection of cited work is not governed by a documented search protocol.
- Evident from the text: the version provided is a preprint (preprints.org, posted 7 March 2023) marked "NOT PEER-REVIEWED," and the author is an employee of Philips Research (declared under Acknowledgements).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
20 Own interpretation · 16 Not checked yet · 3 Own result
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
“The results for the Embase database show a similar trend.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 1. Introduction
plaincorrelational- 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
“Its first mention in a PubMed title, abstract or keywords was in 2018, in a paper about machine learning in neuroscience [11].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 1. Introduction
What the sources say
- Not checked yetcites [11] Vu, 2018, A Shared Vision for Machine Learning in Neuroscience, J. Neurosci. 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.
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
“XAI is being mentioned more and more in scientific publications, as can be seen in figure 1.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 1. Introduction
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.
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
“Another advantage of XAI is that it can help organizations comply with laws and regulations that require transparency and explainability in AI systems.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 3. Legal and regulatory compliance
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
“This shows the growing importance of XAI in (bio)medicine and healthcare.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 1. Introduction
plaincorrelational- 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
“Within the General Data Protection Regulation (GDPR) of the European Union, transparency is a fundamental principle for data processing [15].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 3. Legal and regulatory compliance
What the sources say
- Not checked yetcites [15] Jung, 2023, Essential properties and explanation effectiveness of explainable artificial intelligence in healthcare: A systematic review, Heliyon 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
“With the advent of deep learning (using multiple layers) and new types of algorithms such as Deep Belief Networks (DBNs) [46] and Generative Adversarial Networks (GANs) [47], made possible by the increasing computer power, artificial intelligence algorithms are gaining complexity.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 11. Increasing complexity in the future
What the sources say
- Not checked yetcites [46] Bell, A., Nov, O., and Stoyanovich, J. (2022). Think about the Stakeholders First! Towards an Algorithmic Transparency Playbook for Regulatory Compliance. arXiv. source
- Not checked yetcites [47] HHS Office for Civil Rights (2002). Standards for privacy of individually identifiable health information—Final rule. Fed. Regist., 67, 53181–53273.
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.
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
“In healthcare, this balance might shift more to the 'crystal ball' as accuracy might be considered more important than transparency and explainability.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 9. 'Glass box' vs. 'crystal ball': balance between explainability and accuracy/performance
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.
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
“Explainability is much more difficult to be measured because the quality of an explanation is somewhat subjective.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 10. How to measure explainability?
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
“In some cases, the need for explainability can come at the cost of reduced performance of the model.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 9. 'Glass box' vs. 'crystal ball': balance between explainability and accuracy/performance
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.
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 combination of an AI model with the human expertise also makes the decision more explainable: the clinician can combine the explainable AI with his/her own domain knowledge.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 6. Collaboration between humans and AI
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
“On the one hand, XAI can help to improve the safety and security of AI systems by making it easier to detect and prevent errors and malicious behavior [25].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 5. Privacy and security: a mixed bag
What the sources say
- Not checked yetcites [25] Antoniadi, A.M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B.A., and Mooney, C. (2021). Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review. Appl. Sci., 11. 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
“In the USA there is the Health Insurance Portability and Accountability Act (HIPAA) privacy rule [19], which is related to the Openness and Transparency Principle in the Privacy and Security Framework.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 3. Legal and regulatory compliance
What the sources say
- Not checked yetcites [19] Lim, 2022, Explainable AI, but explainable to whom? An exploratory case study of xAI in healthcare, Handbook of Artificial Intelligence in Healthcare: Practicalities and Prospects
- Not checked yetcites [20] Arrieta, 2020, Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Inf. Fusion source
plaincorrelational- 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 most cases, the combination (also known as 'AI-assisted decision making') will get the best results [34].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 6. Collaboration between humans and AI
What the sources say
- Not checked yetcites [34] Mencar, C., and Alonso, J.M. (2018, January 6–7). Paving the way to explainable artificial intelligence with fuzzy modeling: Tutorial. Proceedings of the Fuzzy Logic and Applications: 12th International Workshop (WILF 2018), Genoa, Italy.
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
“On the other hand, XAI can also raise privacy and security concerns, as providing explanations for AI decisions may reveal sensitive information or show how to manipulate the system, for example by reverse engineering [26].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 5. Privacy and security: a mixed bag
What the sources say
- Not checked yetcites [26] Amann, J., Blasimme, A., Vayena, E., Frey, D., Madai, V.I., and the Precise, Q.c. (2020). Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Med. Inform. Decis. Mak., 20. 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.
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
“Therefore, in a realworld situation it might not be possible to achieve full explainability because accuracy and performance are usually considered more important.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 9. 'Glass box' vs. 'crystal ball': balance between explainability and accuracy/performance
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
“In practice, the complexity of AI algorithms makes it difficult to adhere fully to this principle.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 3. Legal and regulatory compliance
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.
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
“However, even with a good understanding of an AI system, end users may not necessarily trust the system.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 7. Do explanations always raise trust?
hedged- 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. 11
- Probably not a substantial claim. 16
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
“Since then, it has been mentioned a total of 511 times, of which more than half (310) in papers from 2022 or the first months of 2023.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 1. Introduction
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.
It may state two separate claims as one.
In the paper
“This trust can exist on two levels: trust in the model versus trust in the prediction [14].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 2. From 'black box' to '(translucent) glass box'
What the sources say
- Not checked yetcites [14] Tjoa, 2020, A survey on explainable artificial intelligence (xai): Toward medical xai, IEEE Trans. Neural Netw. Learn. Syst. 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
“A low opacity of the translucent glass box (or high transparency of the model) can lead to a better understanding of the model, which in turn could increase trust.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 2. From 'black box' to '(translucent) glass box'
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. It may state two separate claims as one.
- Rests on an assumption: AI algorithms can be perceived as black boxes, and this limits trust in their reliability, which is a major issue in healthcare where decisions can be life-or-death.
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
“Therefore, explainability might be considered of less importance in healthcare, compared to accuracy.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
hedged- 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.
In the paper
“The post-hoc models need to explained by resorting to diverse means to enhance their interpretability, such as text explanations, visual explanations, local explanations, explanations by example, explanations by simplification and feature relevance explanations techniques.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 4. Explainability: transparent or post-hoc
What the sources say
- Not checked yetcites [22] Vale, 2022, Explainable artificial intelligence (XAI) post-hoc explainability methods: Risks and limitations in non-discrimination law, AI Ethics 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.
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
“Within healthcare, trust is a fundamental issue because important decisions might be taken based on the output of the AI algorithm.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 7. Do explanations always raise trust?
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: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: AI algorithms can be perceived as black boxes, and this limits trust in their reliability, which is a major issue in healthcare where decisions can be life-or-death.
In the paper
“The EU is currently working on the Artificial Intelligence Act [17] which makes a distinction between non-high-risk and high-risk AI systems.”
- Also stated in: § 3. Legal and regulatory compliance · plain
“On non-high-risk systems only limited transparency obligations are imposed, while for high-risk systems many restrictions are imposed on quality, documentation, traceability, transparency, human oversight, accuracy and robustness.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 3. Legal and regulatory compliance
What the sources say
- Not checked yetcites [17] 2019, Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view, IEEE Access 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.
- Also stated in: § 3. Legal and regulatory compliance · plain
In the paper
“Linear models and rule-based models are very transparent, but usually have a lower performance than deep learning algorithms (figure 5 of [39]).”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 9. 'Glass box' vs. 'crystal ball': balance between explainability and accuracy/performance
What the sources say
- Not checked yetcites [39] Solayman, 2023, Automatic COVID-19 prediction using explainable machine learning techniques, Int. J. Cogn. Comput. Eng.
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: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Combining explainability of algorithms with privacy-preserving methods such as federated learning [27] might help.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 5. Privacy and security: a mixed bag
What the sources say
- Not checked yetcites [27] 2021, Dissecting scientific explanation in AI (sXAI): A case for medicine and healthcare, Artif. Intell. 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.
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
“A bias could be introduced by having a training dataset with low diversity, or by subjective responses of clinicians to a questionnaire.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
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: 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. It may state two separate claims as one.
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
“End users just want to be sure that the predictions done by the algorithm are accurate, which can be proven by showing them correct predictions from the past.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
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: 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. It may state two separate claims as one.
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
“Robustness of an algorithm in healthcare can be proven by presenting good results based on long-term use in different patient populations.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
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: 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.
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 increasing complexity might make it almost impossible for end users in healthcare (clinicians as well as patients) to understand and trust the algorithms.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
hedgedconditional- 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.
- Rests on an assumption: AI algorithms can be perceived as black boxes, and this limits trust in their reliability, which is a major issue in healthcare where decisions can be life-or-death.
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
“However, making AI explainable is a difficult task, and it will be even more difficult when the complexity of AI algorithms will continue to increase.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
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.
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
“With algorithms getting more complex, it might also be more difficult to make them explainable.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 11. Increasing complexity in the future
hedgedconditional- 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.
In the paper
“For example, trust in algorithms could also be raised by ensuring robustness and by encouraging fairness [50].”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
What the sources say
- Not checked yetcites [50] Charmet, 2022, Explainable artificial intelligence for cybersecurity: A literature survey, Ann. Telecommun. source
hedgedconditional- 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
“Van der Veer et al. [40] concluded that citizens may indeed value explainability of AI systems in healthcare less than in non-healthcare domains and less than often assumed by professionals, especially when weighed against system accuracy”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 9. 'Glass box' vs. 'crystal ball': balance between explainability and accuracy/performance
What the sources say
- Not checked yetcites [40] Gao, 2022, A review of the application of deep learning in the detection of Alzheimer's disease, Int. J. Cogn. Comput. Eng.
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.
It may state two separate claims as one.
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
“Fairness of an AI algorithm is concurrent with bias minimization.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
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.
None of the sources cited for this claim have been checked yet.
In the paper
“Privacy laws such as GDPR, HIPAA and PIPL all include clauses that state that the handling of healthcare data should be transparent, which means that AI algorithms that work with these data should be transparent and explainable as well.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
What the sources say
- Not checked yetcites [15] Jung, 2023, Essential properties and explanation effectiveness of explainable artificial intelligence in healthcare: A systematic review, Heliyon source
- Not checked yetcites [19] Lim, 2022, Explainable AI, but explainable to whom? An exploratory case study of xAI in healthcare, Handbook of Artificial Intelligence in Healthcare: Practicalities and Prospects
- Not checked yetcites [21] Phillips, P.J., Hahn, C.A., Fontana, P.C., Broniatowski, D.A., and Przybocki, M.A. (2020). Four Principles of Explainable Artificial Intelligence, National Institute of Standards and Technology. 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
“Arrieta et al. [22] classified studies on XAI into two approaches: some works focus on creating transparent models, while most works wrap black-box models with a layer of explainability, the so-called post-hoc models.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 4. Explainability: transparent or post-hoc
What the sources say
- Not checked yetcites [22] Vale, 2022, Explainable artificial intelligence (XAI) post-hoc explainability methods: Risks and limitations in non-discrimination law, AI Ethics 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
“Especially in healthcare, accuracy (and to a lesser extent performance) is crucial as it could be a matter of life and death.”
§ Explainable Artificial Intelligence (XAI) in Healthcare > 12. Discussion
hedged- 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. It may state two separate claims as one.
The paper relies on this without support.
AI algorithms can be perceived as black boxes, and this limits trust in their reliability, which is a major issue in healthcare where decisions can be life-or-death.
“However, AI has one big risk: it can be perceived as a 'black box', limiting trust in its reliability, which is a very big issue in an area in which a decision can mean life or death.”
“They can be perceived as a 'black box': something goes in, and something comes out, with no understanding of what happens inside.”
“This distrust in AI algorithms, their accuracy and reliability, is a very big issue in an area in which a decision could mean life or death of the patient.”
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
“Explainable AI can enhance trust by making AI recommendations understandable [304].”
From AI Fairness in Data Management and Analytics: A Review on Challenges, Methodologies and Applications (2023) · cites this paper as [304]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Explainable Artificial Intelligence (XAI) in Healthcare > References
“2020 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW)”
§ Explainable Artificial Intelligence (XAI) in Healthcare > References
“2018, 293-300.”
Citations
Cites
Generative adversarial networks
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020) · Communications of the ACM · doi:10.1145/3422622 · Cited by 18,384
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423 · cited 1×
“[20] classified studies on XAI into two approaches—some works focus on creating transparent models, while most works wrap black-box models with a layer of explainability, the so-called post-hoc models (Figure 2).”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Artificial intelligence in healthcare
Yu, K.-H., Beam, A. L., & Kohane, I. S. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0305-z · Cited by 2,817
Zadeh, L. (1997) · Fuzzy Sets Syst. · doi:10.1016/s0165-0114(97)00077-8 · Cited by 2,771 · cited 1×
“[35] discuss the multi-granularity three-way decisions paradigm [36] and how this acts as a part of granular computing models, playing a significant role in explainable decision-making.”
BackgroundA Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Explainability for artificial intelligence in healthcare: a multidisciplinary perspective
the Precise4Q consortium, Amann, J., Blasimme, A., Vayena, E., Frey, D., & Madai, V. I. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01332-6 · Cited by 2,203
XAI—Explainable artificial intelligence
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, G.-Z. (2019) · Science Robotics · doi:10.1126/scirobotics.aay7120 · Cited by 2,053 · cited 1×
“As a result of this distrust, the term Explainable Artificial Intelligence (XAI) [10] has been gaining momentum as a possible solution.”
BackgroundSecure, privacy-preserving and federated machine learning in medical imaging
Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0186-1 · Cited by 1,676 · cited 1×
“Combining the explainability of algorithms with privacy-preserving methods such as federated learning [52] might help.”
Method
Research works printed but not linked: 7
- Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.-R., and Samek, W. (2020, January 12–18). Explainable AI methods—A brief overview. Proceedings of the xxAI—Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, Vienna, Austria.
- Zadeh, L.A. (1979). Fuzzy Sets, Fuzzy Logic, and Fuzzy Systems: Selected Papers, World Scientific.
- Mencar, C., and Alonso, J.M. (2018, January 6–7). Paving the way to explainable artificial intelligence with fuzzy modeling: Tutorial. Proceedings of the Fuzzy Logic and Applications: 12th International Workshop (WILF 2018), Genoa, Italy.
- Fauvel, K., Masson, V., and Fromont, E. (2020). A performance-explainability framework to benchmark machine learning methods: Application to multivariate time series classifiers. arXiv.
- Huynh, T.D., Tsakalakis, N., Helal, A., Stalla-Bourdillon, S., and Moreau, L. (2022). Explainability-by-Design: A Methodology to Support Explanations in Decision-Making Systems. arXiv.
- Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv.
- Marcus, G. (2020). The next decade in AI: Four steps towards robust artificial intelligence. arXiv.
Cited by
Sorted by citations
Mienye, I. D., Obaido, G., Jere, N., Mienye, E., Aruleba, K., Emmanuel, I. D., & Ogbuokiri, B. (2024) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2024.101587 · Cited by 212
A literature review on applications of explainable artificial intelligence (XAI)
Kalasampath, K., Spoorthi, K. N., Sajeev, S., Kuppa, S. S., Ajay, K., & Maruthamuthu, A. (2025) · IEEE Access · doi:10.1109/access.2025.3546681 · Cited by 180
“As mentioned in [82], XAI enhances trust and usability in crop recommendation systems, as it provides farmers with the ability to interpret the model’s predictions based on specific agricultural needs.”
Mathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11732-2 · Cited by 168
AI Fairness in Data Management and Analytics: A Review on Challenges, Methodologies and Applications
Chen, P., Wu, L., & Wang, L. (2023) · Applied Sciences · doi:10.3390/app131810258 · Cited by 155
Santos, M. R., Guedes, L. A., & Sánchez-Gendriz, I. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6010016 · Cited by 104
“To address this challenge, researchers have introduced explainable artificial intelligence (XAI) [15].”
Background
Metadata
- Authors
- Hulsen, T.
- Affiliations
- Philips (Netherlands) (NL)
- Corresponding author
- Hulsen, Tim
- ORCID
- Hulsen, Tim
- Venue
- AI
- Publisher
- MDPI AG
- Published
- 2023-08-10
- Volume
- 4
- Issue
- 3
- Pages
- 652-666
- ISSN
- 2673-2688 (ISSN-L)
- OpenAlex
- W4385766743
- Semantic Scholar
- 747ce5b1d0178cb08dcf48e43f738f1476876ed5
- Cited by
- 305
- References
- 78
- Citations by year
- 2026: 92 · 2025: 112 · 2024: 85 · 2023: 16
- FWCI
- 26.99
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- AI (publishedVersion, cc-by)
- Preprints.org (acceptedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- explainable AI, artificial intelligence in healthcare, clinical decision support, black box problem, trust in AI, interpretability, medical image analysis, radiology report analysis
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
