Explainable AI: A Review of Machine Learning Interpretability Methods
Open accessThe DOI matches its Crossref record; 170 of the 170 references it cites were found in a registry or an index.
Abstract
Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into “black box” approaches and causing uncertainty regarding the way they operate and, ultimately, the way that they come to decisions. This ambiguity has made it problematic for machine learning systems to be adopted in sensitive yet critical domains, where their value could be immense, such as healthcare. As a result, scientific interest in the field of Explainable Artificial Intelligence (XAI), a field that is concerned with the development of new methods that explain and interpret machine learning models, has been tremendously reignited over recent years. This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“While valuable, these techniques can sometimes be inconsistent or fail to capture the true decision-making process of highly complex models, potentially leading to a false sense of interpretability66.”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [66]
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 methods facilitate a deeper understanding of the model’s internal logic, support debugging and optimization processes, and help identify key variables that most strongly influence students’ behavioral intentions toward GenAI adoption (Linardatos et al., 2020).”
From A two-step structural equation modeling and explainable machine learning framework for understanding university students’ adoption of generative AI: balancing intrinsic motivations and perceived risks (2026) · cites this paper as Linardatos et al., 2020
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
“Yet, there is no common taxonomy neither within one field (such as data science) nor between different fields (law and data science).”
From Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations (2022) · cites this paper as Linardatos et al., 2021
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
“Despite the substantial amount of research devoted to solving the black-box issue of AI, many scholars in the field agree that a clear relevant taxonomy is missing (Doshi-Velez and Kim, 2017; Adadi and Berrada, 2018; Linardatos et al., 2021).”
From Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations (2022) · cites this paper as Linardatos et al., 2021
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
“Prior research on XAI across industries, has also found that the perceived quality of explanations is closely tied to their actionability and practical relevance for end users [8].”
From Explainable AI in hospital clinical decision support systems: A scoping review of healthcare professionals’ perspectives (2026) · cites this paper as [8]
Experimental — accuracy not yet measured
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“An improvement over the initial method was proposed in [24], where the well-known Krizhevsky network [25] was utilised in order to outperform state-of-the-art saliency models by a large margin, increasing the amount of explained information by 67% when compared to state-of-the art.”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 1×
“On the one hand, there are the so called black-box models, which include deep learning [2] and ensembles [8–10].”
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 3×
“[59] PDPbox InterpretML Skater PH G Agnostic tab 589.”
Grad-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×
“The breakDown method, as proposed in [62], is similar to SHAP [48], as both, based on the conditioned responses of a black-box model, attempt to attribute them proportionally to the input features.”
Classification and Regression by randomForest
Liaw, A. I., & Wiener, M. C. (2007) · Cited by 18,594
"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 8×
“[44] showed that, while the Deconvolution [32], Guided BackPropagation [31], and LRP [37] methods help in interpreting deep neural networks, they do not produce the theoretically correct interpretation, even in the simplest neural network setting; a linear model developed while using data that were produced by a linea…”
InfluentialLearning 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 2×
“In many cases, this is achieved through exploiting the gradient information flowing through the layers of the network, Grad-CAM [35], a direct extension of [34], being a prime and most influential example in terms of citations per year.”
Research works printed but not linked: 3
- Luss, R., Chen, P.Y., Dhurandhar, A., Sattigeri, P., Zhang, Y., Shanmugam, K., and Tu, C.C. (2019). Generating contrastive explanations with monotonic attribute functions. arXiv.
- Van Looveren, A., and Klaise, J. (2019). Interpretable counterfactual explanations guided by prototypes. arXiv.
- Wang, X., Jin, H., and He, K. (2019). Natural language adversarial attacks and defenses in word level. arXiv.
Cited by
Items 101–200 of 1,016
Human-XAI Interaction: A Review and Design Principles for Explanation User Interfaces
Chromik, M., & Butz, A. M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85616-8_36 · Cited by 207
“They formalize and ground the concept of XAI [1, 3], relate it to adjacent concepts and disciplines [1, 62], categorize methods [36, 57], analyze the user perspective [33], review evaluation practices [65], or outline future research directions [1, 3].”
BackgroundWani, S. U. D., Khan, N. A., Thakur, G., Gautam, S. P., Ali, M., Alam, P., Alshehri, S., Ghoneim, M. M., & Shakeel, F. (2022) · Healthcare · doi:10.3390/healthcare10040608 · Cited by 119
Nordin, N., Zainol, Z. B., Noor, M. H. M., & Chan, L. F. (2022) · Asian Journal of Psychiatry · doi:10.1016/j.ajp.2022.103316 · Cited by 140
Survey on deep learning based computer vision for sonar imagery
Steiniger, Y., Kraus, D., & Meisen, T. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105157 · Cited by 143
EXplainable Artificial Intelligence (XAI)—From Theory to Methods and Applications
Ortigossa, E. S., Gonçalves, T., & Nonato, L. G. (2024) · IEEE Access · doi:10.1109/access.2024.3409843 · Cited by 124
“…continuously operate using controlled and high-quality data; therefore, complex models are more advantageous due to their high approximation flexibility Simple learning models do not compete with complex ones in terms of predictive performance and generalizability capacity in multiple domains [32].”
BackgroundMethodInfluentialRaihan, M. J., Khan, M. A.-M., Kee, S., & Nahid, A.-A. (2023) · Scientific Reports · doi:10.1038/s41598-023-33525-0 · Cited by 158
Hariri‐Ardebili, M. A., Mahdavi, G., Nuss, L. K., & Lall, U. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106813 · Cited by 142
Naser, M. A., Majeed, A. A., Alsabah, M. Q., Al-Shaikhli, T. R., & Kaky, K. M. (2024) · Algorithms · doi:10.3390/a17020078 · Cited by 166
“Explainable AI (XAI) is essential in cardiovascular disease prediction, attracting significant research attention [204].”
Explainable AI for Medical Data: Current Methods, Limitations, and Future Directions
Hossain, M. I., Zamzmi, G., Mouton, P. R., Salekin, M. S., Sun, Y., & Goldgof, D. B. (2025) · ACM Computing Surveys · doi:10.1145/3637487 · Cited by 184
“” Hence, explainability or interpretability can be defined as the additional information to reason the decision process, feature relevance, or identifying influential features generated by the ML model itself or another algorithm.”
Lu, S.-C., Swisher, C. L., Chung, C. D., Jaffray, D. A., & Sidey-Gibbons, C. J. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1129380 · Cited by 150
“Over the past decades since ML has been available, several approaches addressing interpretability issues of the ML-based models have been proposed and implemented (22).”
BackgroundMethodInfluentialExplainable Artificial Intelligence and Cardiac Imaging: Toward More Interpretable Models
Salih, A. M., Galazzo, I. B., Gkontra, P., Lee, A. M., Lekadir, K., Raisi‐Estabragh, Z., & Petersen, S. E. (2023) · Circulation Cardiovascular Imaging · doi:10.1161/circimaging.122.014519 · Cited by 149
Zideh, M. J., Chatterjee, P., & Srivastava, A. K. (2023) · IEEE Access · doi:10.1109/access.2023.3347989 · Cited by 136
“The main reasons for their limited success are [8], [9]: (i) inability to generalize to out-of-sample datasets by only capturing the intrinsic features of available training or input data, (ii) inability to learn system limitations solely based on available data, thereby producing physically…”
BackgroundLötsch, J., Kringel, D., & Ultsch, A. (2021) · BioMedInformatics · doi:10.3390/biomedinformatics2010001 · Cited by 115
Explainable Artificial Intelligence for Fault Diagnosis of Industrial Processes
Jang, K., Pilario, K. E., Lee, N., Moon, I., & Na, J. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3240601 · Cited by 148
“To solve this problem, there have been an increasing number of studies on ML concerned with addressing this issue, which is known as explainable artificial intelligence (XAI) [18], [19].”
Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey
Melo, A., Câmara, M. M., & Pinto, J. C. (2024) · Processes · doi:10.3390/pr12020251 · Cited by 140
Analyzing Employee Attrition Using Explainable AI for Strategic HR Decision-Making
Díaz, G. M., Galán-Hernández, J. J., & Salvador, J. L. G. (2023) · Mathematics · doi:10.3390/math11224677 · Cited by 166
A review of ultrasonic sensing and machine learning methods to monitor industrial processes
Bowler, A. L., Pound, M. P., & Watson, N. J. (2022) · Ultrasonics · doi:10.1016/j.ultras.2022.106776 · Cited by 124
A review of explainable artificial intelligence in smart manufacturing
Madathil, A. P., Luo, X., Liu, Q., Walker, C. T., Madarkar, R., & Qin, Y. (2025) · International Journal of Production Research · doi:10.1080/00207543.2025.2513574 · Cited by 146
“…as an inherent characteristic rather than an additional feature, defining whether a model’s operations and decisions are understandable to humans, thus por-traying it as a fundamental aspect of model trans-parency (Barredo Arrieta et al. 2020; Linardatos, Papastefanopoulos, and Kotsiantis 2020).”
Evaluating Trustworthiness in AI: Risks, Metrics, and Applications Across Industries
Nastoska, A., Jancheska, B., Rizinski, M., & Trajanov, D. (2025) · Electronics · doi:10.3390/electronics14132717 · Cited by 167
Our New Artificial Intelligence Infrastructure: Becoming Locked into an Unsustainable Future
Robbins, S., & van Wynsberghe, A. (2022) · Sustainability · doi:10.3390/su14084829 · Cited by 136
“Other methods are more general, for instance LIME and SHAP, which aim to highlight feature importance for a particular output (for a review of such methods see e.g., [61]).”
Explainable diabetes classification using hybrid Bayesian-optimized TabNet architecture
Joseph, L. P., Joseph, E. A., & Prasad, R. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106178 · Cited by 106
Advances of machine learning in materials science: Ideas and techniques
Chong, S. S., Ng, Y. S., Wang, H., & Zheng, J. (2023) · Frontiers of Physics · doi:10.1007/s11467-023-1325-z · Cited by 125
“, applied after model fitting) XAI methods proposed for the general ML community [303], including gradient-based attribution (Gradients, Integrated Gradients, and DeepLIFT), deconvolution-based methods (Guided Backpropagation, Deconvolution, Class Activation”
MethodInterpretable machine learning for real estate market analysis
Lorenz, F., Willwersch, J., Cajias, M., & Fuerst, F. (2022) · Real Estate Economics · doi:10.1111/1540-6229.12397 · Cited by 129
Deep Learning Approaches for Medical Image Analysis and Diagnosis
Thakur, G. K., Thakur, A., Kulkarni, S., Khan, N., & Khan, S. (2024) · Cureus · doi:10.7759/cureus.59507 · Cited by 167
“Explainable AI (XAI) techniques such as attention mechanisms, saliency maps, and gradient-based visualization methods can help elucidate the rationale behind model predictions and improve transparency [34].”
BackgroundMachucho-Cadena, R., & González, O. (2025) · Systems · doi:10.3390/systems13040264 · Cited by 142
Mutalib, N. H. A., Sabri, A. Q. M., Wahab, A. W. A., Abdullah, E. R. M. F., & AlDahoul, N. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10890-4 · Cited by 137
Silva, A., Schrum, M., Hedlund-Botti, E., Gopalan, N., & Gombolay, M. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2101698 · Cited by 104
“For more thorough surveys on the recent advances in xAI, we refer readers to Holzinger et al. (2020), Linardatos et al. (2020), and Hoffman et al. (2018).”
BackgroundReview on Interpretable Machine Learning in Smart Grid
Xu, C., Liao, Z., Li, C., Zhou, X., & Xie, R. (2022) · Energies · doi:10.3390/en15124427 · Cited by 126
“Due to the increasing complexity of ML models, post-model interpretability has become the main direction of current interpretable ML research and is mainly focused on the field of deep learning [87].”
BackgroundBlack-Box Access is Insufficient for Rigorous AI Audits
Casper, S., Ezell, C., Siegmann, C., Kolt, N., Curtis, T. L., Bucknall, B., Haupt, A., Wei, K., Scheurer, J., Hobbhahn, M., et al. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3659037 · Cited by 86
“White-box access expands and strengthens the toolbox by allowing for gradient-based techniques [70, 79, 173, 347].”
BackgroundRakholia, R., Suárez‐Cetrulo, A. L., Singh, M., & Carbajo, R. S. (2024) · IEEE Access · doi:10.1109/access.2024.3458830 · Cited by 132
“Decision trees provide transparency and inter-pretability [32].”
MethodArtificial Intelligence and Heart Failure: A State-of-the-Art Review
Khan, M. S., Arshad, M. S., Greene, S. J., Spall, H. G. C. V., Pandey, A., Vemulapalli, S., Perakslis, E. D., & Butler, J. (2023) · European Journal of Heart Failure · doi:10.1002/ejhf.2994 · Cited by 124
“86 Clinicians will be more likely to trust AI algorithms that have been approved by regulatory bodies such as the FDA, and that have undergone rigorous certification processes.”
BackgroundExplainable machine learning framework to predict personalized physiological aging
Bernard, D., Doumard, E., Ader, I., Kémoun, P., Pagès, J., Galinier, A., Cussat‐Blanc, S., Furger, F., Ferrucci, L., Aligon, J., et al. (2023) · Aging Cell · doi:10.1111/acel.13872 · Cited by 119
Khan, F. S., Mazhar, S. S., Mazhar, K., AlSaleh, D., & Mazhar, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11215-9 · Cited by 150
Blockchain, artificial intelligence, and healthcare: the tripod of future—a narrative review
Bathula, A., Gupta, S. K., Merugu, S., Saba, L., Khanna, N. N., Laird, J. R., Sanagala, S. S., Singh, R. K., Garg, D., Fouda, M. M., et al. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10873-5 · Cited by 121
Enhancing Regional Climate Downscaling through Advances in Machine Learning
Rampal, N., Hobeichi, S., Gibson, P. B., Baño‐Medina, J., Abramowitz, G., Beucler, T., González-Abad, J., Chapman, W. E., Harder, P., & Gutiérrez, J. M. (2024) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-23-0066.1 · Cited by 181
Survey on Explainable AI: Techniques, challenges and open issues
Abusitta, A., Li, M. Q., & Fung, B. C. M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124710 · Cited by 98
Ullah, I., Liu, K., Yamamoto, T., Shafiullah, M., & Jamal, A. (2022) · Transportation Letters · doi:10.1080/19427867.2022.2111902 · Cited by 113
Choudhary, R., Kumar, A., Priyadharsini, C., Naik, M. M., Choudhury, M., & Khan, N. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-09463-4 · Cited by 119
“To improve transparency, Explainable XAI techniques, especially SHAP, have gained attention for attributing model outcomes to specific inputs using cooperative game theory 42–44 .”
Housing Price Prediction Using Machine Learning Algorithms in COVID-19 Times
García, R. T. M., Céspedes-López, M. F., & Perez-Sanchez, V. R. (2022) · Land · doi:10.3390/land11112100 · Cited by 110
“There is a wide collection of libraries dedicated algorithms [67].”
BackgroundWu, X., Feng, Z., Liu, J., Chen, H., & Liu, Y. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105516 · Cited by 96
Towards fully automated unmanned aerial vehicle-enabled bridge inspection: Where are we at?
Zhang, C., Zou, Y., Wang, F., Castillo, E. D. R., Dimyadi, J., & Chen, L. (2022) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2022.128543 · Cited by 99
Explainable deep learning in plant phenotyping
Mostafa, S., Mondal, D., Panjvani, K., Kochian, L. V., & Stavness, I. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1203546 · Cited by 109
Gala, D., & Makaryus, A. N. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20156438 · Cited by 88
Kalakoti, R., Bahsi, H., & Nõmm, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3360626 · Cited by 93
“However, the quality of these explainability methods has emerged as a concern, as these methods use additional instruments (e.g., linear models at the point of interest, reflect game theory in identifying the importance score), which may introduce errors into the explanations [19].”
BackgroundExplainable Diabetic Retinopathy Detection and Retinal Image Generation
Niu, Y., Gu, L., Zhao, Y., & Lu, F. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3110593 · Cited by 111
Thalpage, N. S. (2023) · Journal of Digital Art & Humanities · doi:10.33847/2712-8148.4.1_4 · Cited by 132
Analyzing and assessing explainable AI models for smart agriculture environments
Cartolano, A., Cuzzocrea, A., & Pilato, G. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17978-z · Cited by 92
Revolutionizing Groundwater Management with Hybrid AI Models: A Practical Review
Zaresefat, M., & Derakhshani, R. (2023) · Water · doi:10.3390/w15091750 · Cited by 106
A Survey on Cybersecurity in IoT
Dritsas, E., & Τρίγκα, Μ. (2025) · Future Internet · doi:10.3390/fi17010030 · Cited by 121
Rane, N. L., Choudhary, S., & Rane, J. (2024) · doi:10.61577/scpnmia.2024.100006 · Cited by 113
Ennaji, S., Gaspari, F. D., Hitaj, D., Bidi, A. K., & Mancini, L. V. (2025) · IEEE Access · doi:10.1109/access.2025.3600984 · Cited by 137
“Common methods include Limited-memory Broyden–Fletcher– Goldfarb Shanno [71], Fast Gradient Sign Method [35], Basic Iterative Method, Projected Gradient Descent [72], Deepfool [73], Carlini and Wagner [74], and Jacobian-based Saliency Map Attack [75].”
Quantitative evaluation of explainable graph neural networks for molecular property prediction
Rao, J., Zheng, S., Lu, Y., & Yang, Y. (2022) · Patterns · doi:10.1016/j.patter.2022.100628 · Cited by 90
“On the other hand, though XAI methods are widely considered helpful to improve model prediction performance,(29) the current XAI methods, despite affording interpretable predictions, have not really led to improvements in prediction performance.(30) For example, Yu et al.”
MethodExplainable AI for Glaucoma Prediction Analysis to Understand Risk Factors in Treatment Planning
Kamal, M. S., Dey, N., Chowdhury, L., Hasan, S. I., & Santosh, K. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3171613 · Cited by 96
Härtung, T. (2023) · ALTEX · doi:10.14573/altex.2309191 · Cited by 110
“The field of xAI aims to address these interpretability issues (Linardatos et al., 2020; Angelov et al., 2021; Saranya and Sub-AI methods offer computational solutions by automating data extraction, normalization, integration and mining.”
BackgroundA Survey of Industrial AIoT: Opportunities, Challenges, and Directions
Awaisi, K. S., Ye, Q., & Sampalli, S. (2024) · IEEE Access · doi:10.1109/access.2024.3426279 · Cited by 109
Deep learning for financial forecasting: A review of recent trends
Giantsidi, S., & Tarantola, C. (2025) · International Review of Economics & Finance · doi:10.1016/j.iref.2025.104719 · Cited by 118
Survey and Synthesis of State of the Art in Driver Monitoring
Halin, A., Verly, J., & Droogenbroeck, M. V. (2021) · Sensors · doi:10.3390/s21165558 · Cited by 107
“There is, however, a trend toward designing ML algorithms that produce results that can be explained (123; 245).”
Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization
Esmaeili, M., Vettukattil, R., Banitalebi, H., Krogh, N. R., & Geitung, J. T. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11111213 · Cited by 91
“Post hoc explainable evaluations of AI outcomes may profoundly contribute to the understanding of deep learning predictions and eventually enhance their transparency, reliability, and interpretability, and human–machine interactions [7,8].”
Bukhari, S. N. H., Jain, A., Haq, E., Mehbodniya, A., & Webber, J. L. (2022) · Pathogens · doi:10.3390/pathogens11020146 · Cited by 103
Aslam, N., Khan, I. U., Mirza, S., AlOwayed, A., Anis, F. M., Aljuaid, R. M., & Baageel, R. (2022) · Sustainability · doi:10.3390/su14127375 · Cited by 90
Deep Learning in Population Genetics
Korfmann, K., Gaggiotti, O. E., & Fumagalli, M. (2023) · Genome Biology and Evolution · doi:10.1093/gbe/evad008 · Cited by 110
“However, very recent advances in “interpretable machine learning” algorithms (Linardatos et al. 2021) are providing the tools needed to overcome this hurdle.”
BackgroundKumar, B., Lorusso, E., Fosso, B., & Pesole, G. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1343572 · Cited by 103
“Complex machine learning models, such as deep neural networks, might lack interpretability, making it challenging to understand the biological significance of the learned patterns as these models may not be able to generalize to new, unseen data (Linardatos et al., 2021).”
BackgroundCausal Discovery in Manufacturing: A Structured Literature Review
Vuković, M., & Thalmann, S. (2022) · Journal of Manufacturing and Materials Processing · doi:10.3390/jmmp6010010 · Cited by 143
“Explainable AI (xAI) is an attempt to address these issues; however, it is focused on the understanding and interpretation of the AI models rather than the causal behavior of the underlying systems [11].”
Recent advances in machine learning applications in metabolic engineering
Patra, P., B.R., D., Kundu, P., Das, M., & Ghosh, A. (2023) · Biotechnology Advances · doi:10.1016/j.biotechadv.2022.108069 · Cited by 82
Explainable uncertainty quantifications for deep learning-based molecular property prediction
Yang, C.-I., & Li, Y. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00682-3 · Cited by 105
“Equipped with explainability that fits human intuition, the internal mechanisms of models become more understandable and trustworthy when applied to safety-critical tasks that demand careful decision-making [38].”
BackgroundA Critical Survey on Fairness Benefits of Explainable AI
Deck, L., Schoeffer, J., De‐Arteaga, M., & Kühl, N. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658990 · Cited by 142
Facilitating topic modeling in tourism research:Comprehensive comparison of new AI technologies
Kirilenko, A., & Stepchenkova, S. O. (2024) · Tourism Management · doi:10.1016/j.tourman.2024.105007 · Cited by 88
Eke, C. I., & Shuib, L. M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10868-x · Cited by 125
“The opacity of AI’s decision-making process, or the ‘‘black-box’’ dilemma [53] has been a pillar of AI’s successful implementation in clinical practice since the tech-nology’s early and encouraging findings in healthcare.”
Hindi, M., Mohammed, L., Maaz, O., & Alwarafy, A. (2025) · IEEE Access · doi:10.1109/access.2025.3550145 · Cited by 140
“…performance, parallelizability, and faster training times for sequence transduction tasks compared with traditional recurrent or convolutional neural networks [5], [6], [7], [8], [9], thereby opening the door to more powerful LLM-driven applications in various domains, including the legal domain.”
Černevičienė, J., & Kabašinskas, A. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.827584 · Cited by 109
“…model-agnostic explanations) is one of the most common explainability methods associated with black-box AI models and that the model can be used to explain any classifier, irrespective of the algorithm used for predictions (Ribeiro et al., 2016; Gramegna and Giudici, 2021; Linardatos et al., 2021).”
MethodRodis, N., Sardianos, C., Grammatikis, P. I. R., Sarigiannidis, P. G., Varlamis, I., & Papadopoulos, G. T. (2024) · IEEE Access · doi:10.1109/access.2024.3467062 · Cited by 123
“Data dependency : MXAI methods can be adapted so as to operate only for specific data types [99], e.g. visual, text, tabular, audio, etc., i.e. they can essentially be data type-specific approaches.”
MethodYu, J., Shvetsov, A. V., & Alsamhi, S. H. (2024) · IEEE Access · doi:10.1109/access.2024.3482987 · Cited by 113
“Many ML algorithms, such as deep neural networks, are inherently complex and lack interpretability, making it challenging to understand the rationale behind their decisions [111].”
BackgroundAhmed, U., Zheng, J., Almogren, A., Sadiq, M., Rehman, A. U., Sadiq, M. T., & Choi, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-81151-1 · Cited by 108
“Traditional artificial intelligence models can be highly performant, but at the same time, they are considered black boxes: hard to understand and the reason behind making decisions 38 .”
AI-Enabled Energy Policy for a Sustainable Future
Danish, M. S. S., & Senjyu, T. S. (2023) · Sustainability · doi:10.3390/su15097643 · Cited by 88
“Once the dataset has been identified, it must be collected and cleaned to ensure accuracy, representativeness, and quality.”
MethodMulti-Modal Machine Learning in Engineering Design: A Review and Future Directions
Song, B., Zhou, R., & Ahmed, F. (2023) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4063954 · Cited by 120
Toward interpretable LSTM-based modeling of hydrological systems
Fuente, L. D. L., Ehsani, M. R., Gupta, H. V., & Condon, L. E. (2024) · Hydrology and earth system sciences · doi:10.5194/hess-28-945-2024 · Cited by 105
Thingujam, D., Gouli, S., Cooray, S. P., Chandran, K. B., Givens, S., Renganathan, V. G., Tan, Z., Wang, Y., Patam, K., Greer, S. A., et al. (2025) · Plants · doi:10.3390/plants14172699 · Cited by 110
“Common AI-based approaches for disease control include decision trees, random forests, k-nearest neighbors, support vector machines, and artificial neural networks [214].”
Liu, W., Zhao, F., Shankar, A., Maple, C. R., Peter, J. D., Kim, B., Słowik, A., Parameshachari, B. D., & Lv, J. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3336721 · Cited by 92
Use of machine learning in osteoarthritis research: a systematic literature review
Binvignat, M., Pedoia, V., Butte, A. J., Louati, K., Klatzmann, D., Berenbaum, F., Mariotti‐Ferrandiz, E., & Sellam, J. (2022) · RMD Open · doi:10.1136/rmdopen-2021-001998 · Cited by 83
“13 In supervised ML, usually, the data used are separated in two parts with a training dataset to teach the algo-rithm and a testing dataset to test the performance of the model.”
MethodLa inteligencia artificial generativa y la educación universitaria: ¿Salió el genio de la lámpara?
Mendiola, M. S., & Carbajal-Degante, E. (2023) · Perfiles Educativos · doi:10.22201/iisue.24486167e.2023.especial.61692 · Cited by 135
“…por el razonamiento huma-no, sin embargo, hay estudios que demuestran que en el espacio latente de características (espacio donde se generan los elementos distinguibles dentro de las redes neuronales), existe una lógica alternativa que no podemos en-tender del todo (Linardatos et al., 2020 ).”
BackgroundAlonso, M. Á., Vilares, D., Gómez‐Rodríguez, C., & Vilares, J. (2013) · Electronics · doi:10.3390/electronics · Cited by 83
Yun, K. K., Yoon, S. W., & Won, D. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118803 · Cited by 94
An interpretable forecasting framework for energy consumption and CO2 emissions
Aras, S., & Van, M. H. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.120163 · Cited by 89
Enhancing portfolio management using artificial intelligence: literature review
Šutienė, K., Schwendner, P., Șipoș, C., Lorenzo, L., Mirchev, M., Lameski, P., Kabašinskas, A., Tidjani, C., Öztürkkal, B., & Černevičienė, J. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1371502 · Cited by 112
Athanasopoulou, K., Michalopoulou, V.-I., Scorilas, A., & Adamopoulos, P. G. (2025) · Current Issues in Molecular Biology · doi:10.3390/cimb47060470 · Cited by 95
“Explainable AI methods—such as SHAP analysis—are increasingly necessary to trace predictions back to interpretable molecular features [163].”
Nor, A. K. M., Pedapati, S. R., Muhammad, M. B., & Leiva, V. (2021) · Sensors · doi:10.3390/s21238020 · Cited by 100
Understanding CNN fragility when learning with imbalanced data
Dablain, D. A., Jacobson, K. N., Bellinger, C., Roberts, M., & Chawla, N. V. (2023) · Machine Learning · doi:10.1007/s10994-023-06326-9 · Cited by 99
“…variety of approaches to explain model decisions, including: explaining more complicated models by reference to simpler ones, feature relevance, various post-hoc methods, explanation by example, and mapping predictions to inputs (Gunning & Aha, 2019; Adadi & Berrada, 2018; Linardatos et al., 2020).”
Chakraborty, C., Bhattacharya, M., Lee, S., Wen, Z., & Lo, Y.-H. (2024) · Molecular Therapy — Nucleic Acids · doi:10.1016/j.omtn.2024.102295 · Cited by 99
Gacu, J. G., Monjardin, C. E. F., Mangulabnan, R. G. T., Pugat, G. C. E., & Solmerin, J. G. (2025) · Water · doi:10.3390/w17111707 · Cited by 98
Terranova, N., Renard, D., Shahin, M. H., Menon, S., Cao, Y., Hop, C. E. C. A., Hayes, S., Madrasi, K., Stodtmann, S., Tensfeldt, T., et al. (2024) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.3053 · Cited by 78
“54 Model-specific approaches are tailored to a specific ML model and leverage its structure or logic to generate explanations that are then dependent on the model’s design or implementation.”
BackgroundInterpretable machine learning for genomics
Watson, D. (2021) · Human Genetics · doi:10.1007/s00439-021-02387-9 · Cited by 96
Hamida, S. U., Chowdhury, M. J. M., Chakraborty, N. R., Biswas, K., & Sami, S. K. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8110149 · Cited by 95
Tamagusko, T., Correia, M. G., & Ferreira, A. (2024) · Infrastructures · doi:10.3390/infrastructures9120213 · Cited by 99
Guiding principles for the responsible development of artificial intelligence tools for healthcare
Badal, K., Lee, C. M., & Esserman, L. J. (2023) · Communications Medicine · doi:10.1038/s43856-023-00279-9 · Cited by 77
“To ensure that AI tools make patient understanding and values central, AI researchers can utilize different explainability tools 45 and prioritize simpler, more intuitive algorithms.”
MethodHergSPred: Accurate Classification of hERG Blockers/Nonblockers with Machine-Learning Models
Zhang, X., Mao, J., Wei, M., Qi, Y., & Zhang, J. Z. H. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00256 · Cited by 77
Garrett, K. A., Bebber, D. P., Etherton, B. A., Gold, K. M., Sulá, A. I. P., & Selvaraj, M. G. (2022) · Annual Review of Phytopathology · doi:10.1146/annurev-phyto-021021-042636 · Cited by 89
The Evolution of HCI and Human Factors: Integrating Human and Artificial Intelligence
Chignell, M., Wang, L., Zare, A., & Li, J. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3557891 · Cited by 73
“For example, explainable AI is an area that seeks to help people understand the reasoning behind machine learning predictions, so that they are able to trust the results at appropriate times and more effectively manage the decision making process [13,49,89].”
BackgroundLarge-Scale Prediction of Stream Water Quality Using an Interpretable Deep Learning Approach
Zheng, H., Liu, Y., Wan, W., Zhao, J., & Xie, G. (2022) · Journal of Environmental Management · doi:10.1016/j.jenvman.2023.117309 · Cited by 79
Artificial intelligence for medicine: Progress, challenges, and perspectives
Huang, T., Xu, H., Wang, H., Huang, H., Xu, Y., Li, B., Hong, S., Feng, G., Kui, S., Liu, G., et al. (2023) · The Innovation Medicine · doi:10.59717/j.xinn-med.2023.100030 · Cited by 88
A critical moment in machine learning in medicine: on reproducible and interpretable learning
Ciobanu-Caraus, O., Aicher, A., Kernbach, J. M., Regli, L., Serra, C., & Staartjes, V. E. (2024) · Acta Neurochirurgica · doi:10.1007/s00701-024-05892-8 · Cited by 97
“As the structural architecture of ML evolves to highly complex non-linear architectures such as convolutional neural networks, the behavior of the algorithm and the underlying causal relationships leading to a specific result become increasingly difficult to explain [40].”
Metadata
- Authors
- Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S.
- Affiliations
- University of Patras (GR)
- Corresponding author
- Linardatos, Pantelis
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2020-12-25
- Volume
- 23
- Issue
- 1
- Pages
- 18
- ISSN
- 1099-4300 (ISSN-L)
- PMC
- PMC7824368
- OpenAlex
- W3116286104
- Cited by
- 2,922
- References
- 162
- Citations by year
- 2026: 485 · 2025: 702 · 2024: 701 · 2023: 565 · 2022: 370 · 2021: 97 · 2020: 1
- FWCI
- 8.89
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Entropy (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- explainable AI, model interpretability, black-box models, medical applications
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.
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.