Survey of Explainable AI Techniques in Healthcare
Open accessThe DOI matches its Crossref record; 119 of the 120 references it cites were found in a registry or an index, and 1 are not checked yet; 8 of the 50 sources its claims cite were checked for support.
Abstract
Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient’s symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.
Verified 2026-10-05 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This survey reviews recent explainable AI (XAI) techniques for healthcare and medical imaging, categorizing them by interpretation type, model specificity, explanation scope, and explanation form. It highlights commonly used methods such as Grad-CAM, LIME, SHAP, attention, prototypes, and radiomics, and discusses human-centered, deployment, quality, and future challenges.
Key findings
- XAI methods are categorized as intrinsic vs. post hoc, model-specific vs. model-agnostic, local vs. global, and feature-based/textual/example-based; post hoc methods such as CAM/Grad-CAM and LIME are most commonly used in medical imaging.
- The paper reports that clinician satisfaction with LIME chart interpretation reached 78%, though many low-satisfaction clinicians gave low scores despite recognizing the explanations.
- In an evaluation of saliency maps, eight interpretable methods (+ Grad-CAM, guided backpropagation, and guided Grad-CAM) were assessed, but performance on the testing datasets was not competitive.
- For Trojan attack detection, backpropagation had a high success rate, CAM detected the entire trigger region but not always accurate localization, and LIME had high success for small triggers; LIME and SHAP showed unstable explanations with limited examples.
Methods
- Design: narrative survey of recent XAI techniques used in healthcare and related medical imaging, summarizing and categorizing XAI types and algorithms.
- Data/sample: literature and tables (Table 1, Table 2, Table 3) covering XAI methods, modalities, and explanations; no primary dataset or systematic review protocol is reported.
- Analysis: qualitative synthesis of principles, deployment, performance, and challenges, including discussion of radiomics and future directions.
Limitations
- The paper states that the definition of XAI is not clear enough and that explainability depends on the prediction task and target users rather than uniform standards.
- The paper states that post hoc application in the medical field requires more effort; TCAV needs more investigation; trainable attention needs more work; SHAP applications are limited to specific problems; LIME’s low repeatability limits interpretability; and evaluating XAI explanations remains a challenge.
- Evident from the text: the survey does not report a systematic search strategy, inclusion/exclusion criteria, or quantitative meta-analysis; it is a narrative overview.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Figure 1 Flowchart of visual comparison between black-box and explainable artificial intelligence, and how the results affect the user. The top branch shows the process of a black-box model. Typically, it provides only results such as classes (e.g., COVID or non-COVID). The other two branches (middle and bottom) represent two XAI methods, referred to in Section 3.1. Specifically, the XAI model (middle) shows the example of saliency map, and the second one (bottom) is the prototype method, as explained in Section 4.1 and Section 4.6, respectively. An example of a CT image obtained from the COVID-19 CT scan dataset [10].](https://figures.cochat.ai/paper-figures/7410cd2efd4c4f5c87ab22ce2e01ec4c/survey-of-explainable-ai-techniques-in-healthcare-figure-1.jpg)

![Figure 3 Categorization of explainable AI methods used in this paper. These criteria and categories are summarized from [25,26,27]. The orange and blue grids represent the criteria and categories, respectively.](https://figures.cochat.ai/paper-figures/89dcecc050d5476e8f47abead15c4155/survey-of-explainable-ai-techniques-in-healthcare-figure-3.jpg)
Verification
Claims the paper makes
5 Valid · 2 Not valid · 36 Not checked · 19 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Notably, the bias may be derived from data, algorithms, and user interactions [24].”
§ Survey of Explainable AI Techniques in Healthcare > 2. XAI Techniques Related to Medical Imaging > 2.3. Bias and Fairness
What the sources say
- Supportedcites [24] Mehrabi N. Morstatter F. Saxena N. Lerman K. Galstyan A. A survey on bias and fairness in machine learning ACM Comput. Surv. (CSUR) 2021 54 1 35 10.1145/3457607 source
Section 3 of Mehrabi et al. is titled 'BIAS IN DATA, ALGORITHMS, AND USER EXPERIENCES' (p. heading, passage [3]), and its opening text (passage [2]) states that biases in training data are learned and amplified by algorithms, that algorithms can display biased behaviour from design choices even on unbiased data, and that user interactions feed back into new biased data. Subsections 3.1.2 and 3.1.3 (passages [1], [6], [7]) explicitly define algorithmic bias and user interaction bias and describe user-generated data as a bias source, matching the claim's three origins. (LLM, conf=0.92)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In [15], the authors identified three types of security risks related to black-box AI: network attacks, system bias, and mismatch attacks.”
§ Survey of Explainable AI Techniques in Healthcare > 2. XAI Techniques Related to Medical Imaging > 2.1. Confidentiality and Privacy
What the sources say
- Partly supportedcites [15] Kiener M. Artificial intelligence in medicine and the disclosure of risks AI Soc. 2021 36 705 713 10.1007/s00146-020-01085-w 33110296 PMC7580986 sourceExperimental — accuracy not yet measured
The “Three risks of black box AI” section identifies cyber-attacks, systematic bias, and mismatch as risks; page numbers are unavailable in our copy. But it describes mismatch as an AI recommendation that fails to fit a patient’s circumstances, not as an attack, and does not classify all three as security risks. (LLM, conf=0.88)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, there are many practical problems related to the speed of operation and implementation [106].”
§ Survey of Explainable AI Techniques in Healthcare > 6. Discussion, Challenges, and Prospects > 6.2. AI System Deployment
What the sources say
- Partly supportedcites [106] Sutton R.T. Pincock D. Baumgart D.C. Sadowski D.C. Fedorak R.N. Kroeker K.I. An overview of clinical decision support systems: Benefits, risks, and strategies for success NPJ Digit. Med. 2020 3 17 10.1038/s41746-020-0221-y 32047862 PMC7005290 sourceExperimental — accuracy not yet measured
The Introduction says AI-based clinical decision support systems face challenges with explainability and have yet to reach widespread implementation. “Fragmented workflows” says such systems can increase the time clinicians need to complete tasks. These passages support practical implementation and time-related problems for clinical decision support, but do not establish a problem with the operating speed of XAI itself. (LLM, conf=0.83)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For example, CAM is effective in detecting the entire trigger region, but may not always provide the accurate localization of the trigger [112].”
§ Survey of Explainable AI Techniques in Healthcare > 6. Discussion, Challenges, and Prospects > 6.3. Quality of Explanation
What the sources say
- Partly supportedcites [112] Lin Y.S. Lee W.C. Celik Z.B. What do you see? Evaluation of explainable artificial intelligence (XAI) interpretability through neural backdoors arXiv 2020 2009.10639 sourceExperimental — accuracy not yet measured
Section 4.3 reports that Grad-CAM completely covers the trigger region for ResNet50 models, but highlights only a small area inside the trigger for VGG16 and AlexNet. This supports the localization caveat, not an unqualified claim that it detects the entire region. Section 2 also distinguishes Grad-CAM, the method evaluated, from CAM. (LLM, conf=0.85)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Most of the recently proposed medical imaging works use post-interpretation rather than model-based interpretation (e.g., CAM and GCAM models are widely used).”
§ Survey of Explainable AI Techniques in Healthcare > 6. Discussion, Challenges, and Prospects
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.
18 more claims
Create a free account to see all 62 claims and to verify the 42 references still open.
- Probably not a substantial claim. 30
- It may state two separate claims as one. 13
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Explainable AI in healthcare has been surveyed extensively, yet no existing review addresses the challenges posed by decoder-based LLMs.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [46]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These dimensions were categorized according to established and previously validated XAI taxonomies [12,17,18], which were adapted to the context of agentic AI systems as a provisional analytic schema to enable consistent classification across heterogeneous implementations.”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Nonetheless, these reviews consistently highlight persistent challenges relating to faithfulness, stability, and standardized evaluation of explanations.”
From Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review (2026) · cites this paper as [62]
Experimental — accuracy not yet measured
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
§ Survey of Explainable AI Techniques in Healthcare > 4. Introduction of the Explainable AI Method: A Brief Overview > 4.5. Triplet Networks
“the other two samples are randomly chosen from the training set in the same “Positive” and different “Negative” categories.”
§ Survey of Explainable AI Techniques in Healthcare > 4. Introduction of the Explainable AI Method: A Brief Overview > 4.5. Triplet Networks
“Since labeling is not necessary, this method can be used for unsupervised learning.”
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“Typically, this approach combines CNNs and long short-term memory networks (LSTM) for encoding the image and text, respectively [81].”
BackgroundGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 3×
“[28] BP * * * [29] Guided-BP * * * [30] Deconv Network * * * [31] LRP * * * [32] CAM * * * [33] Grad-CAM * * * [34] LIME * * * [35] GraphLIME * * * [36] SHAP * * * Feature”
Method"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
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 3×
“[28] BP * * * [29] Guided-BP * * * [30] Deconv Network * * * [31] LRP * * * [32] CAM * * * [33] Grad-CAM * * * [34] LIME * * * [35] GraphLIME * * * [36] SHAP * * * Feature”
BackgroundGauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
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 · cited 3×
“For example, backpropagation [28], class activation mapping [32], and layer-wise relevance propagation [31] are all post hoc interpretation techniques.”
MethodArrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321 · cited 1×
“Typically, XAI is an explainable model providing insights into how the predictions are made to achieve trustworthiness, causality, transferability, confidence, fairness, accessibility, and interactivity [5,6].”
BackgroundRudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 2×
“However, it is suggested to develop an interpretable model for any high-risk medical situation [8].”
BackgroundBarredo 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×
“Typically, XAI is an explainable model providing insights into how the predictions are made to achieve trustworthiness, causality, transferability, confidence, fairness, accessibility, and interactivity [5,6].”
Background
Research works printed but not linked: 6
- Devlin J. Chang M. Lee K. Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv 2018 1810.04805
- Yang X. He X. Zhao J. Zhang Y. Zhang S. Xie P. COVID-CT-dataset: A CT scan dataset about COVID-19 arXiv 2020 2003.13865
- Simonyan K. Vedaldi A. Zisserman A. Deep inside convolutional networks: Visualising image classification models and saliency maps arXiv 2013 1312.6034
- Jiang C. Chen Y. Chang J. Feng M. Wang R. Yao J. Fusion of medical imaging and electronic health records with attention and multi-head machanisms arXiv 2021 2112.11710
- Shapley L.S. 17. A value for n-person games Contributions to the Theory of Games (AM-28), Volume II Princeton University Press Princeton, NJ, USA 2016 307 318
- Nguyen H.T.T. Cao H.Q. Nguyen K.V.T. Pham N.D.K. Evaluation of Explainable Artificial Intelligence: SHAP, LIME, and CAM Proceedings of the FPT AI Conference 2021 Ha Noi, Viet Nam 6–7 May 2021 1 6
Cited by
Items 101–200 of 631
A survey of post-hoc xai methods from a visualization perspective: Challenges and opportunities
Bhati, D., Amiruzzaman, M., Zhao, Y., Guercio, A., & Le, T. (2025) · IEEE Access · doi:10.1109/access.2025.3581136 · Cited by 24
“Other surveys, such as those by Chaddad et al. [12] and Salahuddin et al. [13], have focused on domain-specific applications, emphasizing the importance of transparency and multimodal approaches in AI explanations.”
Explorable Explainable AI: Improving AI Understanding for Community Health Workers in India
Solano-Kamaiko, I. R., Mishra, D., Dell, N. L., & Vashistha, A. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642733 · Cited by 37
“While these methods have been widely adopted by the XAI community [10, 23, 50], given our understanding of AWWs and their limited levels of AI literacy, we felt that the current methods would not resonate with AWWs.”
MethodAlrashdi, I., & Alqazzaz, A. (2024) · Sustainable Machine Intelligence Journal · doi:10.61356/smij.2024.77106 · Cited by 32
Bonada, M., Rossi, L. F., Carone, G., Panico, F., Cofano, F., Fiaschi, P., Garbossa, D., Meco, F. D., & Bianconi, A. (2024) · Biomedicines · doi:10.3390/biomedicines12081878 · Cited by 30
“Although nearly all radiologic data use a universal format, DICOM, there are a growing number of exceptions, making it more difficult to standardize processes.”
BackgroundAliyeva, K. R., & Mehdiyev, N. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119987 · Cited by 31
Machine learning for antidepressant treatment selection in depression
Arnold, P. I. M., Janzing, J., & Hommersom, A. (2024) · Drug Discovery Today · doi:10.1016/j.drudis.2024.104068 · Cited by 28
Vajrobol, V., Saxena, G. J., Singh, S., Pundir, A., Gupta, B. B., Gaurav, A., & Chui, K. T. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.10.042 · Cited by 27
Shahsavari, Y., Baseri, Y., Hafid, A. S., Dambri, O. A., & Makrakis, D. (2026) · Journal of Medical Internet Research · doi:10.2196/80178 · Cited by 31
“The advent of big data analytics [321], cloud computing [322] and improved algorithms have enabled more sophisticated and accurate AI tools [323].”
Explainable Image Captioning to Identify Ergonomic Problems and Solutions for Construction Workers
Yong, G., Liu, M., & Lee, S. H. (2024) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-5744 · Cited by 25
Literature Review of Explainable Tabular Data Analysis
Quinn, H. O., Sedky, M., Francis, J., & Streeton, M. (2024) · Electronics · doi:10.3390/electronics13193806 · Cited by 31
Dutta, J., & Puthal, D. (2024) · IEEE Access · doi:10.1109/access.2024.3520799 · Cited by 27
“Transparency is essential for creating trust, ensuring causal relationships, strengthening transferability, raising confidence, encouraging fairness, improving accessibility, aiding interpretability, and allowing meaningful engagement between patients and healthcare systems [12].”
Dick, K., Kaczmarek, E., Ducharme, R., Bowie, A. C., Dingwall‐Harvey, A. L. J., Howley, H. E. A., Hawken, S., WALKER, M. C., & Armour, C. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-90216-8 · Cited by 23
“By also incorporating an explainable artificial intelligence (XAI) approach when training DL models, model developers and end users (e.g., healthcare practitioners) can gain insight into how various patient characteristics and other factors contribute to model predictions 27,28 .”
Li, Y., Yi, X., Fu, J., Yang, Y., Duan, C., & Wang, J. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1594450 · Cited by 40
“For example, saying “This AI system achieves 97% accuracy overall, but it may be less reliable for patients over 75 years old” helps contextualize results, supports informed consent, and reinforces patient autonomy (39).”
Explainable artificial intelligence in electrocardiography: A systematic review
Taleban, A., Sparapani, R., Noffke, P., Zlochiver, S., Lu, Q., Widlansky, M. E., & Luo, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109325 · Cited by 33
A hybrid approach of vision transformers and CNNs for detection of ulcerative colitis
Shah, S. A., Taj, I., Usman, S. M., Shah, S. N. H., Imran, A. S., & Khalid, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-75901-4 · Cited by 29
Choose your explanation: a comparison of SHAP and Grad-CAM in human activity recognition
Tempel, F., Groos, D., Ihlen, E. A. F., Adde, L., & Strümke, I. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06968-3 · Cited by 29
“Still, understanding the inner workings of such systems is crucial, particularly when they are used in high-risk and sensitive environments such as healthcare, where the outcomes of model decisions can have significant ethical and practical implications [4, 5, 6, 7].”
AI analysis of super-resolution microscopy: Biological discovery in the absence of ground truth
Nabi, I. R., Cardoen, B., Khater, I. M., Gao, G., Wong, T. H., & Hamarneh, G. (2024) · The Journal of Cell Biology · doi:10.1083/jcb.202311073 · Cited by 26
“Beyond natural image analysis, XAI has found rapid adoption in medical image analysis (Chaddad et al., 2023), a field that shares defining characteristics of SRM-based analysis: scarcity of ground truth, targeted at discovery, and high societal impact of findings.”
BackgroundGuleria, P., Srinivasu, P. N., & Hassaballah, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17212-w · Cited by 23
“XAI approaches seek to explain model predictions to aid medical practitioners in understanding and having faith in the judgments made by AI systems [11].”
Guo, T., Bardhan, I. R., Ding, Y., & Zhang, S. (2024) · Information Systems Research · doi:10.1287/isre.2023.0029 · Cited by 33
Enhancing Medicare Fraud Detection With a CNN-Transformer-XGBoost Framework and Explainable AI
Sakil, M. B. H., Hasan, M. A., Mozumder, M. S. A., Hasan, M. R., Opee, S. A., Mridha, M. F., & Aung, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3562577 · Cited by 20
“As healthcare professionals and patients increasingly rely on AI-driven solutions, the demand for explainable AI (XAI) has surged, emphasizing the need for models that not only perform well but also provide insights into their decision-making processes [9], [10].”
Jim, J. R., Rayed, M. E., Mridha, M. F., & Nur, K. M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0322488 · Cited by 24
“Furthermore, the integration of XAI techniques, such as Saliency Maps and Gradient-weighted Class Activation Mapping (GRAD-CAM), enhances the transparency of these models [12].”
In Silico Peptide Design: Methods, Resources, and Role of AI
Choudhury, P. R., Mishra, S. K., Yadav, S., Singh, S., & Mathur, P. (2025) · Journal of Peptide Science · doi:10.1002/psc.70063 · Cited by 22
Next Generation Healthcare with Explainable AI: IoMT-Edge-Cloud Based Advanced eHealth
Dutta, J., Puthal, D., & Yeun, C. Y. (2023) · Globecom · doi:10.1109/globecom54140.2023.10436967 · Cited by 21
“These mentioned frameworks provide interpretations for specific predictions made by traditional AI (”black box”) models [8].”
Backgroundالدور الوسيط للذكاء الاصطناعي القابل للتفسير في العلاقة بين حوكمة البيانات والأداء المؤسسي
الجداوي, م. ن. (2024) · المجلة العربية للعلوم الإدارية. · doi:10.34120/ajas.v30i1.213 · Cited by 22
Explainable artificial intelligence for LDL cholesterol prediction and classification
Sezer, S., Öter, A., Ersöz, B., Topçuoğlu, C., Bülbül, H. İ., Sağıroğlu, Ş., Akın, M., & Yılmaz, G. (2024) · Clinical Biochemistry · doi:10.1016/j.clinbiochem.2024.110791 · Cited by 22
Husain, A. N., Knake, L. A., Sullivan, B. A., Barry, J. S., Beam, K., Holmes, E., Hooven, T. A., McAdams, R. M., Moreira, A. G., Shalish, W., et al. (2024) · Pediatric Research · doi:10.1038/s41390-024-03774-4 · Cited by 24
CIRSE Position Paper on Artificial Intelligence in Interventional Radiology
Najafi, A., Cazzato, R. L., Meyer, B. C., Pereira, P. L., Alberich, A., López‐Rueda, A., Ronot, M., Fritz, J. M., Maas, M., Benson, S., et al. (2023) · CardioVascular and Interventional Radiology · doi:10.1007/s00270-023-03521-y · Cited by 21
“, explainable AI, XAI) by providing insights into how AI predictions are achieved [12].”
BackgroundGiorgetti, C., Contissa, G., & Basile, G. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1545409 · Cited by 21
“Post hoc explanations are instead obtained through external methods when analyzing the model (30).”
Paving the Roadmap for XAI and IML in Healthcare: Data-Driven Discoveries and the FIXAIH Framework
Alghamdi, S., Mehmood, R., Alqurashi, F. A., & Alzahrani, A. (2025) · IEEE Access · doi:10.1109/access.2025.3616353 · Cited by 28
“This refers to the disconnect between the increasing complexity of AI systems and the ability of health-care professionals to understand, trust, and effectively apply them in clinical settings [10], [38], [39].”
InfluentialRubinić, I., Kurtov, M., Rubinić, I., Likić, R., Dargan, P. I., & Wood, D. M. (2023) · British Journal of Clinical Pharmacology · doi:10.1111/bcp.15899 · Cited by 24
“28,29 XAI plays a pivotal role in mitigating decision-making influenced by discrimination, ensuring that models and algorithms make impartial decisions irrespective of specific features.”
BackgroundA texture-based method for predicting molecular markers and survival outcome in lower grade glioma
Chaddad, A., Hassan, L., & Katib, Y. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04844-6 · Cited by 19
“Despite the widespread adoption of CNNs for medical image analysis [33], they have certain limitations, particularly in relation to small datasets that can lead to overfitting and biased results.”
BackgroundSelf-citationIntegration of Federated Learning and Blockchain in Healthcare: A TutorialPreprint
Shahsavari, Y., Dambri, O. A., Baseri, Y., Hafid, A. S., & Makrakis, D. (2024) · doi:10.36227/techrxiv.171340632.25905526/v1 · Cited by 27
Bauer, J. M., & Michalowski, M. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf110 · Cited by 22
Xu, Y. (2024) · International Journal of COPD · doi:10.2147/copd.s458935 · Cited by 20
“35 When using AI in medical decision-making, it is necessary to clarify issues of responsibility attribution and compliance.”
MethodJomeiri, A., Navin, A. H., & Shamsi, M. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111065 · Cited by 21
Kim, D., Handayani, M. P., Lee, S.-B., & Lee, J. (2023) · Sensors · doi:10.3390/s23031072 · Cited by 19
“This approach is making its way into a wide variety of domains, including education [18]; lithology [19] and geology [20]; social science [21]; construction engineering [22,23]; transportation [24] and smart cities [25]; healthcare [26] and medical [27]; mass media and entertainment [28]; tourism, travel, and hospital…”
BackgroundHuman-centric and semantics-based explainable event detection: a survey
Kolajo, T., & Daramola, O. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10525-0 · Cited by 23
“Similarly, Chaddad et al. ( 2023 ) surveyed explainable AI techniques focusing on healthcare and related medical imaging applications.”
BackgroundExtensive Review of Literature on Explainable AI (XAI) in Healthcare Applications
Mariappan, R. (2024) · Recent Advances in Computer Science and Communications · doi:10.2174/0126662558296699240314055348 · Cited by 20
Rousta, F., Esteki, A., Shalbaf, A., Sadeghi, A., Moghadam, P. K., & Voshagh, A. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108205 · Cited by 18
Applying Large Language Models for Causal Structure Learning in Non Small Cell Lung Cancer
Naik, N., Khandelwal, A., Joshi, M., Atre, M., Wright, H., Kannan, K. K., Hill, S., Mamidipudi, G., Srinivasa, G., Bifulco, C. B., et al. (2024) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi61247.2024.00110 · Cited by 30
“The current “black box” approach to modelling has limited interpretability and has not achieved acceptance in clinical settings [3], [4].”
BackgroundKwan, H. Y., Shell, J., Fahy, C., Yang, S., & Xing, Y. (2025) · Systems · doi:10.3390/systems13040281 · Cited by 20
SHAP-based Explanations are Sensitive to Feature Representation
Hwang, H., Bell, A. S., Fonseca, J., Pliatsika, V., Stoyanovich, J., & Whang, S. E. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732105 · Cited by 26
Repetto, S., Maljkovic, I., Lotto, M., Ciná, A. E., Vascon, S., & Roli, F. (2025) · Machine Learning · doi:10.1007/s10994-025-06919-6 · Cited by 19
“Thanks to this success, DNNs have been applied in the medical industry (Al Kuwaiti et al. 2023) with the potential to change healthcare systems and bring about significant breakthroughs in diagnosis, treatment, and patient care (Alowais et al. 2023).”
InfluentialComputer Vision Tasks for Ambient Intelligence in Children’s Health
Germanese, D., Colantonio, S., Coco, M. D., Carcagnì, P., & Leo, M. (2023) · Information · doi:10.3390/info14100548 · Cited by 17
“Regarding the related scientific literature, whereas several works summarise applications and systems in medical imaging [6], less work is devoted to surveying approaches for ambient intelligence [7,8].”
BackgroundA unified and practical user-centric framework for explainable artificial intelligence
Kaplan, S., Uusitalo, H. M. T., & Lensu, L. T. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111107 · Cited by 31
Explainable Intrusion Detection for Internet of Medical Things
Memon, S. A., Wiil, U. K., & Shaikh, M. (2023) · International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management · doi:10.5220/0012210300003598 · Cited by 15
“ PSO has been used in various cyber security applications such as ID, malware detection, phishing detection, feature selection, and parameter optimization (Chaddad et al., 2023), (Adnan et al., 2021).”
MethodInnovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization
Alam, M. S., Elsheikh, E. A. A., Suliman, F. M., Rashid, M. M., & Faizabadi, A. R. (2024) · Diagnostics · doi:10.3390/diagnostics14060629 · Cited by 18
“Explainable AI refers to the ability of an AI system to clearly communicate its logic and the methods it uses to make decisions in a way that humans can comprehend [38].”
BackgroundRevolutionizing Innovations and Impact of Artificial Intelligence in Healthcare
-, I. C., -, R. G., -, S. S., -, K. D., & Kundu, M. (2024) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2024.v06i03.19333 · Cited by 27
Chan, V. T. T., Ran, A. R., Wagner, S. K., Hui, H. Y. H., Hu, X., Ko, H., Fekrat, S., Wang, Y. X., Lee, C. S., Young, A. L., et al. (2024) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2024.101290 · Cited by 18
Imans, D., Abuhmed, T., Alharbi, M., & El–Sappagh, S. (2024) · Diagnostics · doi:10.3390/diagnostics14212385 · Cited by 20
Machine Learning‐Engineered Nanozyme System for Synergistic Anti‐Tumor Ferroptosis/Apoptosis Therapy
Li, T., Cao, B., Su, T., Lin, L., Wang, D., Liu, X., Wan, H., Ji, H., He, Z., Chen, Y., et al. (2024) · Small · doi:10.1002/smll.202408750 · Cited by 19
A Comprehensive Framework for Transparent and Explainable AI Sensors in Healthcare
Bouderhem, R. (2024) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/ecsa-11-20524 · Cited by 19
Dattola, S., Ielo, A., Varone, G., Cacciola, A., Quartarone, A., & Bonanno, L. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1547727 · Cited by 17
“XAI techniques can help elucidate how models make decisions, highlighting the most influential features and enabling clinicians to validate model outputs (Tjoa and Guan, 2020; Chaddad et al., 2023).”
Towards Edge AI and Varied Approaches of Digital Wellness in Healthcare Administration: A Study
Vyas, S., Gupta, S., & Shukla, V. K. (2023) · International Conference on Computational Intelligence and Knowledge Economy (ICCIKE) · doi:10.1109/iccike58312.2023.10131857 · Cited by 16
“Whereas there are some prime stake holders of wellness and healthcare ecosystem which are being discussed below [19] [20]: Patient- Any person seeking a medical care at a certain instant of time can be called a patient.”
BackgroundDifferences between human and artificial/augmented intelligence in medicine
Monteith, S., Glenn, T., Geddes, J. R., Achtyes, E. D., Whybrow, P. C., & Bauer, M. (2024) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2024.100084 · Cited by 21
Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review
Mallma, M. J. R., Zuloaga-Rotta, L., Borja-Rosales, R., Mallma, J. R. R., Vilca-Aguilar, M., Salas-Ojeda, M., & Mauricio, D. (2024) · Neurology International · doi:10.3390/neurolint16060098 · Cited by 15
“…be expanded in future research: • The present work did not find results related to the use of Large Language Models (LLM) or Generative AI (GenAI) as a topic related to explainability in the medical field, and it is something that should be studied given the popularity and novelty of these models.”
Murugan, T. K., & Kameswaran, A. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.103378 · Cited by 15
Nekoui, M., Bolouri, S. E. S., Forouzandeh, A., Dehghan, M., Zonoobi, D., Jaremko, J. L., Buchanan, B. M., Nagdev, A. D., & Kapur, J. (2024) · Diagnostics · doi:10.3390/diagnostics14222526 · Cited by 14
Review on computational methods for the detection and classification of Parkinson's Disease
Singh, K., Khare, M., Khare, A., & Kohli, N. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109767 · Cited by 16
Siqueira, L. P., Batista, C. L., Lui, P. H., Kazienko, J. F., Quincozes, S. E., Quincozes, V. E., Welfer, D., & Nomura, S. (2025) · Sensors · doi:10.3390/s25206261 · Cited by 15
“XAI techniques can be categorized by the explanation method, such as feature attribution (e.g., feature maps), textual explanations, and example-based reasoning [49].”
Ethics of Artificial Intelligence: challenges, opportunities and future prospects
Falvo, F. R., & Cannataro, M. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822112 · Cited by 16
“( [29]): however, many AI systems, such as those based on deep neural networks, operate as ”black boxes,” making it difficult to interpret and justify the decisions made by the algorithm ( [11], [ ?”
InfluentialSaleem, M., Watson, A. E., Anwaar, A., Jasser, A. O., & Yusuf, N. (2025) · Biomolecules · doi:10.3390/biom15040589 · Cited by 15
The Use of AI for Phenotype-Genotype Mapping
Sharma, J., & Goel, P. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4690-8_21 · Cited by 19
Machine learning in gastrointestinal endoscopy: challenges and opportunities
Lobanovs, S., Aleksejeva, J., Rūtiņa, A. K., Krustiņš, E., Čižovs, J., & Bļizņuks, D. (2025) · BMJ Open Gastroenterology · doi:10.1136/bmjgast-2025-001923 · Cited by 14
“39 40 41 SHapley Additive exPlanations (SHAP) and saliency maps reveal key features in gastroscopy images, enhancing ML transparency 39 40 42 (figure 2).”
Haile, G., & Mouthadi, M. E. (2023) · International Conference on Information and Communication Technology for Development for Africa (ICT4DA) · doi:10.1109/ict4da59526.2023.10302183 · Cited by 13
AI- and IoT-Enabled Solutions for Healthcare
Kouchaki, S., Ding, X., & Sanei, S. (2024) · Sensors · doi:10.3390/s24082607 · Cited by 13
A Systematic Literature Review of Artificial Intelligence in Prehospital Emergency Care
Elfahim, O., Edjinedja, K. L., Cossus, J., Youssfi, M., Barakat, O., & Desmettre, T. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9090219 · Cited by 14
“This lack of XAI is particularly challenging in the context of EMS, a high-stakes and safety-critical field where opaque “black-box” decision-making can worsen the effects of inaccurate forecasts, undermining physician trust [104].”
Foo, L. F., Choolani, M. A., Papageorghiou, A. T., Divakar, H., Shehata, H. A., Melamed, N., Jones, G. D., Senikas, V., van der Beek, E. M., Palshetkar, N., et al. (2026) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.70942 · Cited by 6
Gurmessa, D. K., & Jimma, W. (2023) · Cogent Engineering · doi:10.1080/23311916.2023.2273088 · Cited by 18
“One proposed solution is to sidestep the need for post-hoc explanations altogether by employing interpretable models from the outset, as suggested by (Chaddad et al., 2023; Mahya & Fürnkranz, 2023b).”
MethodTurchioe, M. R., Hermann, A. D., & Benda, N. C. (2024) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2023.1321265 · Cited by 15
“Explainability measures attempt to “shine a light” into the black box by using additional algorithms to understand how and why an AI model is producing certain output (52, 53).”
BackgroundDeveloping interpretable models and techniques for explainable AI in decision-making
Jagannathan, J., Agrawal Rajesh, K., Labhade-Kumar, N., Rastogi, R., Unni, M. V., & Baseer, K. K. (2023) · THE SCIENTIFIC TEMPER · doi:10.58414/scientifictemper.2023.14.4.39 · Cited by 16
Explainable AI: definition and attributes of a good explanation for health AI
Kyrimi, E., McLachlan, S., Wohlgemut, J. M., Perkins, Z., Lagnado, D. A., Marsh, W., the ExAIDSS Expert Group, Gimson, A. E., Shafti, A., Ercole, A., et al. (2025) · AI and Ethics · doi:10.1007/s43681-025-00668-x · Cited by 17
“Papers on foundational aspects of an explanation are scarce.”
Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
Alagumariappan, P., Sathyamoorthy, M., Dhanaraj, R. K., Kamalanand, K., Emmanuel, C., Allabun, S. M., Othman, M., Getahun, M., & Soufiene, B. O. (2025) · Scientific Reports · doi:10.1038/s41598-025-93495-3 · Cited by 17
“The higher value of AUC shows the better classification capacity of a classifier over two different classes 9 .”
Mardiani, E., Judijanto, L., & Rukmana, A. Y. (2023) · West Science Interdisciplinary Studies · doi:10.58812/wsis.v1i10.301 · Cited by 15
“Explainable AI (XAI) techniques, including interpretable machine learning models and model-agnostic approaches, aim to demystify the decision-making process [29], [30].”
MethodPham, M.-K., Mai, T. T., Crane, M., Ebiele, M., Brennan, R., Ward, M. E., Geary, Ú., McDonald, N., & Bezbradica, M. (2024) · Diagnostics · doi:10.3390/diagnostics14212405 · Cited by 13
“A recent comprehensive survey [6] provides an extensive list of explainable methods for interpreting model predictions and investigating their underlying behaviors.”
BackgroundInfluentialHuang, M., Law, H., & Tam, S. Y. (2025) · Cancers · doi:10.3390/cancers17193121 · Cited by 16
“Moreover, high-dimensional, sparse radiomics datasets increase overfitting risk, threatening model robustness [12].”
Baldus, S. G., Wiesmann, M., Habel, U., Gerhards, A., Hasan, D., Weyland, C. S., Truhn, D., Hasl, M. M., Clemens, B., & Nikoubashman, O. (2026) · Insights into Imaging · doi:10.1186/s13244-025-02159-3 · Cited by 13
“There exists a current trend of explainable AI (xAI), which “ aims to explain the information behind the black-box model of deep learning that reveals how decisions are made ” [28, 29].”
Applications, image analysis, and interpretation of computer vision in medical imaging
Matsuzaka, Y., & Iyoda, M. (2026) · Frontiers in Radiology · doi:10.3389/fradi.2025.1733003 · Cited by 14
Athukorala, V. S., & Ilmini, W. M. K. S. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03344-0 · Cited by 10
“In the Participants domain, most studies (e.g. [3, 7, 11, 12]), demonstrated a low risk of bias, indicating that the study populations were carefully selected and accurately represented real-world ICU patients.”
Explainable Artificial Intelligence (XAI) for Methods Working on Point Cloud Data: A Survey
Mulawade, R. N., Garth, C., & Wiebel, A. (2024) · IEEE Access · doi:10.1109/access.2024.3472872 · Cited by 12
“Even though the XAI field has survey works that cater to specific sub-fields such as cybersecurity related XAI [11], time series data-based XAI [48], and healthcare related XAI [9], [68], we observe the absence of such works in the point cloud-based XAI field.”
BackgroundEnhanced inclusion and accessibility in education and training through virtual worlds
Anastasovitis, E., & Roumeliotis, Μ. (2024) · Metaverse · doi:10.54517/m.v5i2.2836 · Cited by 10
Role of Artificial Intelligence in Transforming Diagnosis, Treatment, and Patient Care: A Review
Ali, S. A., Ali, S., & Khan, S. (2025) · Current pharmacogenomics and personalized medicine (Online)/Current pharmacogenomics and personalized medicine · doi:10.2174/0118756921404728251019182202 · Cited by 17
Geraci, J., Qorri, B., Tsay, M. J., Cumbaa, C. A., Leonczyk, P., Alphs, L. D., Ballard, E. D., Zarate, C. A., & Pani, L. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02143-7 · Cited by 12
Kumbhar, E. A. U. T. (2024) · Journal of Electrical Systems · doi:10.52783/jes.648 · Cited by 10
“This transition not only enhances patient results but also aids in the efficient utilization of healthcare resources by reducing the effects of avoidable illnesses[3], [4].”
BackgroundExplainable AI in Healthcare: A Multi-Disciplinary Perspective
Upendran, S. V. (2024) · Advances in healthcare information systems and administration book series · doi:10.4018/979-8-3693-5468-1.ch004 · Cited by 11
Overall Survival Predictions of GBM Patients Using Radiomics: An Explainable AI Approach Using SHAP
Alahakoon, A. M. H. H., Walgampaya, C., Walgampaya, S., Ekanayake, I. U., & Alawatugoda, J. (2024) · IEEE Access · doi:10.1109/access.2024.3471832 · Cited by 10
“XAI is an explainable model providing insights into how the predictions are made to achieve trust-worthiness, causality, transferability, confidence, fairness, accessibility, and interactivity [51].”
BackgroundSingh, A. K., Sharma, K. K., Bajpai, M. K., & Cabezuelo, A. S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112374 · Cited by 12
Kelly, A., Jensen, E. S., Grua, E. M., Mathiasen, K., & van de Ven, P. W. J. (2025) · JMIR Medical Informatics · doi:10.2196/64617 · Cited by 12
“Post hoc XAI techniques, such as these, represent the vast majority of XAI use cases in health care [33].”
Review on Explainable AI by using LIME and SHAP Models for Healthcare Domain
Shaikh, A. S., Samant, R. M., Patil, K. S., Patil, N. R., & Mirkale, A. R. (2023) · International Journal of Computer Applications · doi:10.5120/ijca2023923263 · Cited by 9
Park, K., Lim, J., Shin, S. H., Ryu, M., Shin, H., Lee, M., Hong, S. W., Hwang, S. W., Park, S. H., Yang, D., et al. (2024) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.16788 · Cited by 9
“32 This study has several limitations.”
Medical needles in the hands of AI: Advancing toward autonomous robotic navigation
Alterovitz, R., Hoelscher, J., & Kuntz, A. (2025) · Science Robotics · doi:10.1126/scirobotics.adt1874 · Cited by 11
Challenges in the Clinical Application of Machine Learning for Pancreatic Cancer
Večurkovská, I., Roškovičová, V., & Kaťuchová, J. (2025) · Bratislavské lekárske listy/Bratislava medical journal · doi:10.1007/s44411-025-00312-4 · Cited by 9
“In biomarker-based diagnostics, SHAP values can be calculated for individual patients to identify which biomarkers (e.g., CA19-9, miRNA) had the highest impact on the risk score prediction, aiding personalized interpretation [26, 38, 49].”
InfluentialOkpete, U. E., & Byeon, H. (2025) · World Journal of Gastroenterology · doi:10.3748/wjg.v31.i35.111033 · Cited by 9
Perrone, B., Amato, F., & Olmo, G. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108954 · Cited by 11
Singh, J., Alsaidan, O. A., Aodah, A. H., Alrobaian, M., Almalki, W. H., Almujri, S. S., Sahoo, A., Alam, K., Lal, J. A., Barkat, M. A., et al. (2025) · Future Oncology · doi:10.1080/14796694.2025.2606642 · Cited by 6
Edge Computing in Healthcare Using Machine Learning: A Systematic Literature Review
Mashmool, A., Delzanno, G., Saadatfar, H., Ahmad, A., Koschke, R., Alizadehsani, R., Acharya, U. R., & D’Agostino, D. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70069 · Cited by 17
Explainable Artificial Intelligence in Medical Image Analysis: State of the Art and Prospects
Volkov, E. N., & Averkin, A. N. (2023) · IEEE International Conference on Soft Computing and Measurements (SCM) · doi:10.1109/scm58628.2023.10159033 · Cited by 11
Deep Learning within a DICOM WSI Viewer for Histopathology
Vállez, N., Espinosa-Aranda, J. L., Pedraza, A., Déniz, Ó., & Bueno, G. (2023) · Applied Sciences · doi:10.3390/app13179527 · Cited by 10
Chen, B., Jin, J., Liu, H., Yang, Z., Zhu, H., Wang, Y., Lin, J., Wang, S., & Chen, S. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1289669 · Cited by 12
Singh, A. K., van de Ven, P. W. J., Eising, C., & Denny, P. (2024) · IEEE Access · doi:10.1109/access.2024.3444042 · Cited by 11
“Furthermore, the explainability of GNNs, as discussed in [52], is a significant advantage over traditional CNNs, especially in the medical domain where understanding the reasoning behind a model’s decisions is crucial for building trust and ensuring safety [53].”
Background
Metadata
- Authors
- Chaddad, A., Peng, J., Xu, J., & Bouridane, A.
- Affiliations
- Guilin University of Electronic Technology (CN)
- University of Sharjah (AE)
- Corresponding author
- Chaddad, Ahmad
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-01-05
- Volume
- 23
- Issue
- 2
- Pages
- 634
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9862413
- OpenAlex
- W4313648826
- Cited by
- 591
- References
- 111
- Citations by year
- 2026: 144 · 2025: 211 · 2024: 159 · 2023: 76
- FWCI
- 12.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- NATIONAL NATURAL SCIENCE FOUNDATION (82260360, QN2021033002L)
- FOREIGN YOUNG TALENTS PROGRAM (82260360, QN2021033002L)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Keywords
- explainable AI, health care, diagnostic imaging, deep learning interpretability, black-box models, medical image analysis, clinical decision support
- MeSH terms
- Algorithms, Artificial Intelligence, Humans, Judgment, Physicians, Research Personnel
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.