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 201–300 of 631
Ong, J., Jang, K. J., Baek, S. J., Hu, D., Lin, V., Jang, S., Thaler, A., Sabbagh, N., Saeed, A., Kwon, M., et al. (2024) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2024.100095 · Cited by 11
“68 Both policymakers and researchers recognize the importance of understanding the decisions made by deep learning models.”
Rodrigues, G. A. P., Serrano, A. L. M., Bispo, G. D., Filho, G. P. R., Gonçalves, V. P., & Meneguette, R. I. (2025) · Bioengineering · doi:10.3390/bioengineering12080795 · Cited by 11
“In the medical field, Grad-CAM has been adopted to visualize the regions of an image that most influenced the model’s decision, providing explainability into the basis of its predictions [18,19].”
Arnaud, É., Moreno-Sánchez, P. A., Elbattah, M., Ammirati, C., van Gils, M., Dequen, G., & Ghazali, D. A. (2025) · Applied Sciences · doi:10.3390/app15158449 · Cited by 11
Acoustic and machine learning methods for speech-based suicide risk assessment: A systematic review
Marie, A., Garnier, M., Bertin, T., Machart, L., Dardenne, G., Quellec, G., & Berrouiguet, S. (2025) · Journal of Affective Disorders · doi:10.1016/j.jad.2025.120569 · Cited by 15
Explainability in context: calibrating appropriate trust and reliance in artificial intelligence
Davis, S. E., & Salwei, M. E. (2026) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocag082 · Cited by 10
“23 For example, SHapley Additive exPlana-tions force plots reveal how specific input values increase or decrease a predicted probability.”
Enhancing Classification Tasks through Domain Adaptation Strategies
Chaddad, A., & Wu, Y. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385628 · Cited by 8
“The interpretability of models holds significant importance, especially in the medical field [1], [15].”
BackgroundSelf-citationDeep Sky Objects Detection with Deep Learning for Electronically Assisted Astronomy
Parisot, O., & Jaziri, M. (2024) · Astronomy · doi:10.3390/astronomy3020009 · Cited by 10
“Inspired by recent works in the industrial [36] and health domains [37], this third approach consists in training a supervised binary classifier to detect the presence of DSO, then applying an eXplainable AI (XAI) technique to automatically identify their position.”
MethodInterpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process
Choudhary, A., Vuković, M., Mutlu, B., Haslgrübler, M., & Kern, R. (2024) · Sensors · doi:10.3390/s24123728 · Cited by 10
“All these methods offer post hoc explanations of why a model produced a specific output [47].”
MethodLee, K., Lee, S., Kwak, J. S., Park, H., Oh, H., & Koh, J. C. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13133850 · Cited by 11
Chang, Q., Ahmad, D., Toth, J. W., Bascom, R., & Higgins, W. E. (2024) · Journal of Imaging · doi:10.3390/jimaging10080191 · Cited by 11
“Chaddad et al. summarize a number of these mechanisms, with the references giving detailed current surveys of this important area [60–62].”
BackgroundUnveiling Parkinson’s: Handwriting Symptoms with Explainable and Interpretable CNN Model
Zemmar, A., Bennour, A., Mekhaznia, T., Ghabban, F. M., & Al-Sarem, M. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001424400019 · Cited by 9
Explainable Vertical Federated Learning for Healthcare: Ensuring Privacy and Optimal Accuracy
Sakib, S. K., & Das, A. B. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825564 · Cited by 8
Chatzara, A., Maliagkani, E., Mitsopoulou, D., Katsimpris, A., Apostolopoulos, I. D., Papageorgiou, E. I., & Georgalas, I. (2025) · Bioengineering · doi:10.3390/bioengineering12050475 · Cited by 9
“Addressing the current limitations will be essential for unlocking the full potential of AI in ophthalmology and facilitating its meaningful adoption in clinical care.”
Artificial intelligence techniques in inherited retinal diseases: a review
Trinh, H., Vice, J., Tajbakhsh, Z., Charng, J., Alam, K., Chen, F. K., & Mian, A. S. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ade9c7 · Cited by 11
“In contrast, deep learning models such as CNNs typically rely on saliency maps to extract relevant learned features [76].”
BackgroundMalik, M. I., Nedadur, R., & Chu, M. W. A. (2025) · Journal of Thoracic and Cardiovascular Surgery · doi:10.1016/j.jtcvs.2025.07.017 · Cited by 12
Finzel, B. (2024) · Künstliche Intell. · doi:10.1007/s13218-024-00835-y · Cited by 11
A practical guide to apply AI in childhood cancer: Data collection and AI model implementation
Wen, S., Theobald, S., Gangas, P., Jiménez, K. C. B., Merks, J. H. M., Schoot, R. A., Meyerheim, M., & Graf, N. M. (2024) · EJC Paediatric Oncology · doi:10.1016/j.ejcped.2024.100197 · Cited by 8
A novel explainable machine learning-based healthy ageing scale
Stepančič, K. G., Ramovš, A., Ramovš, J., & Košir, A. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02714-w · Cited by 7
“Among others, they are also used for explanations for diabetes prediction [28], deep-learning-based medical imaging applications [29] and retinoblastoma diagnosis [30].”
BackgroundXAI Unveiled: Revealing the Potential of Explainable AI in Medicine - A Systematic Review
Scarpato, N., Ferroni, P., & Guadagni, F. (2024) · IEEE Access · doi:10.1109/access.2024.3514197 · Cited by 11
“The explainability approach comprise a range of techniques and methodologies, including feature importance analysis, rule extraction, surrogate models, visualization techniques such as relevant areas identification, and tailored methods (see [238]).”
Vieira, C., da Rocha, L. C. D., Guimarães, M. D. P., & Dias, D. R. C. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109556 · Cited by 7
Exploring the Impact of Explainability in Large Language Model (LLM) Applications on User Experience
Wang, Y., Fang, X., Xu, Z., Li, J., & Wang, L. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719941 · Cited by 12
Daram, S. (2025) · International Journal of AI BigData Computational and Management Studies · doi:10.63282/3050-9416.ijaibdcms-v6i2p102 · Cited by 12
DIKWP-Driven Artificial Consciousness for IoT-Enabled Smart Healthcare Systems
Duan, Y., & Guo, Z. (2025) · Applied Sciences · doi:10.3390/app15158508 · Cited by 8
Fatima, M., Zia, R., & Usmani, I. A. (2025) · Systems and Soft Computing · doi:10.1016/j.sasc.2025.200412 · Cited by 41
WaveMem-SHAPNet: A Transparent Deep Learning Approach to Early Diagnosis of Diabetic Retinopathy
Kirubakaran, M., & Vijayarajan, V. (2026) · SN Computer Science · doi:10.1007/s42979-025-04632-8 · Cited by 7
“The importance of technological advancement in improving DR detection accuracy is recognized because the traditional methods of XAI has been extensively acknowledged in both academia and industry in recent years [3 ].”
Din, S. U., Kemna, R., Ket, J. C. F., Iqbal, M., Bohoudi, O., Hoogendoorn, M., Beretta, E., & Lisowska, A. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1819422 · Cited by 8
“…al., 2023; Bhati et al., 2024; Patrício et al., 2023; Ennab and Mcheick, 2024; Van der Velden et al., 2022; Yang et al., 2022; Singh et al., 2020a; Chaddad et al., 2023; Salahuddin et al., 2022; Nazir et al., 2023; Band et al., 2023; Borys et al., 2023; Bharati et al., 2023a) adopt a broader…”
Explainable AI Applications in Healthcare: A Systematic Review
Eje, O. A., Azim, S. M., & Dehzangi, A. (2026) · Algorithms · doi:10.3390/a19060488 · Cited by 8
The Use of Explainable Artificial Intelligence in Medicine
Wen, B., & Chaddad, A. (2023) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom56612.2023.10472365 · Cited by 7
“Therefore, the proposal of XAI is to address the interpretability issues about by deep learning algorithms, and to enhance understanding of model decisions by providing explanations [1].”
BackgroundSelf-citationRajaguru, H., & Chellappan, D. (2024) · Bioengineering · doi:10.3390/bioengineering11080766 · Cited by 8
“The findings suggest that integrating multimodal datasets can lead to more accurate and comprehensive diabetes risk prediction models [12].”
BackgroundMedBot – An NLP based ChatBot for Diabetes Prediction
Sreekar, K., Aswin, V., Narayanan, V., V, Thangavel, S. K., Somasundaram, K., & Shanmugam, S. K. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10724179 · Cited by 7
Mlynář, J., Depeursinge, A., Prior, J. O., Schaer, R., Joly, A., & Évéquoz, F. (2024) · Frontiers in Communication · doi:10.3389/fcomm.2023.1234987 · Cited by 13
“Explainability has been identified as one of the major challenges in the incorporation of AI into medicine and health care in general, and radiomics more specifically (Kundu, 2021; Jin et al., 2022; Chaddad et al., 2023).”
Kaur, A., & Goyal, S. (2025) · Wiley eBooks · doi:10.1002/9781394249312.ch14 · Cited by 8
Jadwal, P. K., & Saini, H. K. (2025) · Wiley eBooks · doi:10.1002/9781394271382.ch3 · Cited by 7
Data-driven AI platform for dens evaginatus detection on orthodontic intraoral photographs
Ren, R., Liu, J., Li, S., Wu, X., Peng, X., Liao, W., & Zhao, Z. (2025) · BMC Oral Health · doi:10.1186/s12903-024-05231-4 · Cited by 8
“However, completely unexplainable AI algorithms can introduce significant biases [15].”
Healthcare Transformation Through Disruptive Technologies: The Role of Telepresence Robots
Naseer, F., Khan, M. N., & Addas, A. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-63701-8_14 · Cited by 8
Kuyoro, A. O., Boye, F. O., & Onuiri, E. E. (2025) · Acadlore Transactions on AI and Machine Learning · doi:10.56578/ataiml040203 · Cited by 7
EVolutionary independent DEtermiNistiC explanation
Dentamaro, V., Giglio, P., Impedovo, D., & Pirlo, G. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111008 · Cited by 6
Faria, N., Campelos, S., & Carvalho, V. H. (2025) · Information · doi:10.3390/info16090740 · Cited by 8
Hidalgo, P., & Rodríguez, D. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114384 · Cited by 9
Buler, J., Buler, R., Bobowicz, M., & Grochowski, M. (2025) · IEEE Access · doi:10.1109/access.2025.3627387 · Cited by 6
“While post-hoc techniques are widespread, intrinsic interpretability is generally more practical for medical applications, since it provides built-in transparency without relying on external analyses [15].”
Debsarkar, S. S., & Prasath, V. B. S. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102704 · Cited by 7
Regulatory challenges and liability pathways for AI-powered robots in EU medical practice
Nišević, M., Kulenovic, H., Milojevic, D., Levak, J., & Biasin, E. (2026) · AI & Society · doi:10.1007/s00146-026-02869-2 · Cited by 9
“As noted by Korica et al. (2021) and Chaddad et al. (2023), it also undermines medical professionals’ trust, making clinical adoption more difficult.”
Turky, M., Samaranayake, L. P., Osathanon, T., & Dummer, P. M. H. (2026) · Journal of Dentistry · doi:10.1016/j.jdent.2026.106733 · Cited by 18
Hwang, C., Kim, Y. H., Hyun, J. K., Kim, J. H., Lee, S. R., Kim, C. M., Nam, J., & Kim, E. Y. (2023) · Bioengineering · doi:10.3390/bioengineering10101222 · Cited by 7
“However, as the validation results in Table 4 show, if there are equal amounts of data from various breathing groups to train, we expect that the DL models, including our Dilated ResNet model, can achieve better results than the current ones.”
ResultThe Integration of Explainable AI Methods for the Classification of Medical Image Data
Nikolić, M., Jankovic, D. S., Stanimirović, A., & Stoimenov, L. V. (2024) · International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) · doi:10.1109/icetran62308.2024.10645095 · Cited by 6
“The rise in recent years is exponential, as can be seen in [10].”
BackgroundMethodUtilizing Explainable AI and Biosensors for Clinical Diagnosis of Infectious Vector-Borne Diseases
Vaiyapuri, T. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.9026 · Cited by 10
Machine learning evidence towards eradication of malaria burden: A scoping review
James, I., & Osubor, V. I. (2025) · Applied Computer Science · doi:10.35784/acs_6873 · Cited by 8
“…and the interpretation of output to provide precise evidence for accurate malaria control, diagnosis, and drug development. eXplainable AI (Chaddad et al., 2023), though intended to provide transparent machine learning procedures for accurate interpretation of the learning process is…”
A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models
Jiang, Y., Zhao, X., Wu, Y., & Chaddad, A. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i17.33941 · Cited by 6
Self-citationAttai, K. F., Akwaowo, C., Asuquo, D. E., Esubok, N. U., Nelson, U.-A., Dan, E., Obot, O. U., Amannah, C., & Uzoka, F. (2023) · doi:10.59200/icarti.2023.022 · Cited by 6
Deep Survival Analysis With Clinical Variables for COVID-19
Chaddad, A., Hassan, L., Katib, Y., & Bouridane, A. (2023) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2023.3256966 · Cited by 6
“particularly in the context of big data analysis [14], [15], [16].”
BackgroundSelf-citationNeuronAlg: An Innovative Neuronal Computational Model for Immunofluorescence Image Segmentation
Giacopelli, G., Migliore, M., & Tegolo, D. (2023) · Sensors · doi:10.3390/s23104598 · Cited by 6
Explainable AI in Military Training Applications
Khan, A., Jhanjhi, N. Z., Hamid, D. H. T. B. A. H., & Omar, H. A. H. B. H. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-6361-1.ch007 · Cited by 5
Towards a transparent and interpretable AI model for medical image classifications
Wen, B., Wu, Y., Daqqaq, T. S., & Chaddad, A. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10343-w · Cited by 6
“This highlights the need to enhance the transparency of black-box models to increase their reliability, which is the aim of XAI [15], [16].”
Self-citationHaslgrübler, M., Azadi, B., & Ferscha, A. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103897 · Cited by 7
Ghorbankhani, M., & Safara, M. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103320 · Cited by 6
Mazhar, K., Dwivedi, P., & Kant, V. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70548 · Cited by 5
Amalgamation of Transfer Learning and Explainable AI for Internet of Medical Things
Murugan, R., Paliwal, M., Patibandla, R. S. M. L., Shah, P., Balaga, T. R., Gurrammagari, D. R., Singaravelu, P., Yenduri, G., & Jhaveri, R. H. (2023) · Recent Advances in Computer Science and Communications · doi:10.2174/0126662558285074231120063921 · Cited by 6
Potential of Federated Learning in Healthcare
Hu, Y., & Chaddad, A. (2023) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom56612.2023.10472378 · Cited by 5
“Future research in the field of FL will consider explainable artificial intelligence (XAI) models [10], [11].”
BackgroundSelf-citationLee, S. B. (2024) · JAMIA Open · doi:10.1093/jamiaopen/ooae035 · Cited by 6
“47 ResNet’s architecture was designed around the concept of a skip connection, which tackles vanishing gradients in deep networks.”
BackgroundKurasawa, H., Waki, K., Seki, T., Chiba, A., Fujino, A., Hayashi, K., Nakahara, E., Haga, T., Noguchi, T., & Ohe, K. (2024) · JMIR AI · doi:10.2196/56700 · Cited by 7
“Additionally, to increase the interpretability of this method, an approach that combines it with traditional XAI technologies [36] such as SHAP and LIME should be investigated.”
MethodInfluentialOptimisation-Based Feature Selection for Regression Neural Networks Towards Explainability
Liapis, G. I., Tsoka, S., & Papageorgiou, L. G. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7020033 · Cited by 9
Toh, S. Y., Cai, C., Wang, L. R., Bai, X., Ngeow, J. Y. Y., & Fan, X. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719791 · Cited by 12
“To address these issues, Explainable AI (XAI) has been developed to provide insights into how AI systems make decisions [8].”
Canha, D., Kubler, S., Främling, K., & Fagherazzi, G. (2025) · ACM Computing Surveys · doi:10.1145/3737445 · Cited by 10
Bejerano-Blázquez, I., & Familiar-Cabero, M. (2025) · Information · doi:10.3390/info16080684 · Cited by 9
Beimel, D., & Albagli-Kim, S. (2024) · Mathematics · doi:10.3390/math12040502 · Cited by 6
Medical Metaverse: A New Virtual Health Experience
Chaddad, A., & Jiang, Y. (2023) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe60311.2023.00074 · Cited by 6
“…the implementation of a medical metaverse, which can engage in ongoing and comprehensive learning, comprehend health-related issues and medical information, curtail medical expenses and time required for similar cases in the future, and serve as a valuable assistant to medical professionals [20].”
BackgroundSelf-citationEltigani, F. M., Zhang, X., Liu, M., Peng, J., & Su, X. (2024) · Optics & Laser Technology · doi:10.1016/j.optlastec.2024.111208 · Cited by 5
Self-citationShchekochikhin, D., Charaya, K. V., Shilova, A. S., Nesterov, А. P., Pershina, E. S., Sherashov, A. V., Panov, S., Ibraimov, S. G., Bogdanova, A. A., Suvorov, А. Y., et al. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14061934 · Cited by 5
“The interactions between predictors and their relationships with outcomes in medicine are often complex and nonlinear, for which modern machine learning algorithms can provide a solution [10].”
SmartForest: Optimizing anemia diagnosis with enhanced random forest and XGBoost integration
Saputra, D. C. E., Sunat, K., Ratnaningsih, T., Ma’arif, A., & Suwarno, I. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106442 · Cited by 7
An Investigation about Modern Deep Learning Strategies for Colon Carcinoma Grading
Carcagnì, P., Leo, M., Signore, L., & Distante, C. (2023) · Sensors · doi:10.3390/s23094556 · Cited by 6
The use of probabilistic graphical models in pediatric sepsis: a feasibility and scoping review
Nguyen, T. M., Poh, K. L., Chong, S., Loh, S. W., Heng, Y. C. K., & Lee, J. H. (2023) · Translational Pediatrics · doi:10.21037/tp-23-25 · Cited by 6
Application of Attention-Based LSTM Hybrid Models for Stock Price Prediction
Sun, X. (2024) · Advances in Economics Management and Political Sciences · doi:10.54254/2754-1169/104/2024ed0152 · Cited by 6
Skärström, V. W., Johansson, L., Alvén, J., Lorentzon, M., & Häggström, I. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72117-5_30 · Cited by 4
Healthcare Cognitive Decision Support System – The State-of-the-Art
Lobo, A., Sá, D., Cunha, J. P. S., Duarte, R. J. D. S., Duarte, J., & Santos, M. F. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.145 · Cited by 4
Toward trustworthy AI with integrative explainable AI frameworks
Finzel, B. (2025) · it - Information Technology · doi:10.1515/itit-2025-0007 · Cited by 8
Development and Evaluation of an Artificial Intelligence Model to Set Target IOP for Glaucoma
Pham, A. T., Robitaille, E., Bradley, C., de Souza, J., & Yohannan, J. (2025) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2025.08.046 · Cited by 4
Advancements in biomedical rendering: A survey on AI-based denoising techniques
Denisova, E., Francia, P., Nardi, C., & Bocchi, L. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110979 · Cited by 5
Huang, C., Xu, J., Qiu, H., & Yue, Y. (2025) · International Journal of Nursing Practice · doi:10.1111/ijn.70060 · Cited by 5
Self-citationPham, M.-K., Mai, T. T., Crane, M., Brennan, R., Ward, M. E., Geary, Ú., Byrne, D., O'Connell, B. C., Bergin, C. J., Creagh, D., et al. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03214-1 · Cited by 5
“While tools like SHAP and LIME are commonly used for global interpretation [39–41], techniques like DeepXplainer [42] and recommendations by Wani et al. [43] highlight the need for interpretable models in clinical environments.”
UNICORN: Towards universal cellular expression prediction with a multi-task learning framework
Liu, T., Huang, T., Wang, L., Lin, Y., Ying, R., & Zhao, H. (2025) · Nature Communications · doi:10.1038/s41467-025-64506-8 · Cited by 11
The impact of feature combinations on machine learning models for in-hospital mortality prediction
Stenwig, E., Rossi, P. S., Salvi, G., & Skjærvold, N. K. (2025) · Scientific Reports · doi:10.1038/s41598-025-26611-y · Cited by 4
Potluri, S., Panigrahi, B. S., Mohanty, S. N., & Albalawi, A. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3632121 · Cited by 4
“While these practices have indicated their significance separately, very few models combine them in a system that explicitly addresses the necessities of consumer electronics in connected healthcare [3], [4].”
Maurer, N., Brückner, M., Thyssen, C., Becker, S., & Huwer, J. (2026) · Computers and Education Open · doi:10.1016/j.caeo.2026.100376 · Cited by 6
The Need for Explainable AI in Industry 5.0
Khan, A., Jhanjhi, N. Z., Hamid, D. H. T. B. A. H., & Omar, H. A. H. B. H. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-6361-1.ch001 · Cited by 5
Khan, A., Jhanjhi, N. Z., Hamid, D. H. T. B. A. H., & Omar, H. A. H. B. H. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-6361-1.ch006 · Cited by 4
Comparative Study on Lung Disease Detection and Classification Techniques using Deep Explainable
Salkade, S. A., & Rathi, S. (2023) · International Conference on Advances in Science and Technology (ICAST) · doi:10.1109/icast59062.2023.10454908 · Cited by 4
COIN: Counterfactual Inpainting for Weakly Supervised Semantic Segmentation for Medical Images
Shvetsov, D., Ariva, J., Domnich, M., Vicente, R., & Fishman, D. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63800-8_3 · Cited by 11
“These problems are further amplified by the limited access to medical image datasets due to data protection laws [7].”
BackgroundFocused review on artificial intelligence for disease detection in infants
Bartl-Pokorny, K. D., Zitta, C., Beirit, M., Vogrinec, G., Schuller, B. W., & Pokorny, F. B. (2024) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1459640 · Cited by 4
A Pilot Study on Clinician-AI Collaboration in Diagnosing Depression From Speech
Feng, K., & Chaspari, T. (2024) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi62660.2024.10913848 · Cited by 12
“It’s important to note that previous research mainly focused on medical imaging, text, or electronic health records comprised of time series or tabular data [32], [33].”
Rodrigues, E. M., Gouveia, M., Oliveira, H. P., & Pereira, T. (2025) · IEEE Access · doi:10.1109/access.2025.3555428 · Cited by 7
“XAI models offer two primary types of explanations: post-hoc explanations, which are formed from information generated by external methods after training closed-box models, and explanations based on information obtained from the inherently interpretable components of self-explainable models [6].”
Unveiling the Depths of Explainable AI: A Comprehensive Review
Khan, W., & Ishrat, M. (2024) · Advances in systems analysis, software engineering, and high performance computing book series · doi:10.4018/979-8-3693-0968-1.ch004 · Cited by 5
Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review
Collaco, B. G., Prabha, S., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Wood, N. G., Gopala, N., Raman, R., Hester, E. O., & Forte, A. J. (2026) · Bioengineering · doi:10.3390/bioengineering13050513 · Cited by 3
“…procedures), post hoc when explanations were produced after inference without influencing the underlying decision process (e.g., feature attribution, saliency maps, or SHAP/LIME-style methods), and hybrid when both intrinsic and post hoc mechanisms were combined within the same system [12,18].”
InfluentialPai, N. P., Rahimi, S. A., Tulsi, J., Bartlett, S., Grover, S., & Sejdic, E. (2026) · FACETS · doi:10.1139/facets-2025-0142 · Cited by 3
Zubair, M. (2025) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit63348.2025.10989340 · Cited by 3
“Explainable AI [28] could solve this problem by interpreting [29] the diagnostic model outcome to the end-users.”
Chikotie, T. T., Watson, B., Kimanuka, U., & Banda, T. (2025) · IST-Africa Conference (IST-Africa) · doi:10.23919/ist-africa67297.2025.11060542 · Cited by 3
“This method provide transparency into model decisions, highlighting key features that contribute significantly to each prediction, thus making the model outcomes more interpretable for stakeholders [25].”
Explainable AI for Visual Inspection: A Comparative Analysis and Review
Albydhany, M. H., & Al‐Darraji, I. (2025) · Journal of Visualized Experiments · doi:10.3791/69440 · Cited by 7
Thomas, N. R., Anitha, J., Popîrlan, C., Popirlan, C.-I., & Hemanth, D. J. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.070689 · Cited by 5
“When utilized properly, it can contribute to more informed decisions, improved communication among care teams, and ultimately better patient outcomes [97].”
Explainable AI: Bridging Transparency and Trust in AI
Oyenuga, M. O., & OLADELE, T. O. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/406019 · Cited by 3
Explainable brain tumor segmentation via attention-guided hybrid CNN–Transformer–Mamba network
Tehsin, S., Nasir, I. M., & Damaševičius, R. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116000 · Cited by 3
Mohammed, M. A., Alsahafi, Y. S., Salama, R. A., Elshewey, A. M., & Hosny, K. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200670 · Cited by 2
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.