Jul 2026· Journal of Visualized Experiments· Vol 233· 0 citations
Medicine
TL;DR
A reproducible experimental approach to developing and evaluating explainable AI systems for healthcare analytics that integrates the steps of data preprocessing, predictive modeling, interpretation generation, and evaluation into one seamless workflow that can be applied to both structured clinical data and medical imaging datasets.
Abstract
Explainable Artificial Intelligence (XAI) is increasingly recognized as an indispensable tool for building trustworthy AI systems in healthcare, where transparency and the ability to explain decisions are essential components of clinical decision-making. This publication presents a reproducible experimental approach to developing and evaluating explainable AI systems for healthcare analytics. The developed pipeline integrates the steps of data preprocessing, predictive modeling, interpretation generation, and evaluation into one seamless workflow that can be applied to both structured clinical data and medical imaging datasets. Ensemble machine learning models have demonstrated strong predictive performance on structured tabular datasets, whereas deep learning models are effective for learning complex patterns in medical imaging data. Techniques such as SHAP, LIME, and Grad-CAM are global and local explanations that facilitate model interpretation. Very helpful. The quantitative assessment of the framework spans many different metrics such as accuracy, precision, recall, F1 score, ROC-AUC, explanation metrics, fidelity, and stability. The results indicate that when the experimental conditions are controlled, the framework demonstrated improved predictive performance and explanation quality under the evaluated experimental conditions. As a document guided by protocol, this piece of work backs the reproducibility and scalability, the persistent implementation by other living beings. This transparent, understandable AI model is the foundation upon which clinical decision-making support and healthcare analytics systems gain trust and usage on a large scale.
Artificial intelligence has made a great impact on healthcare by providing accurate disease diagnosis, personalised treatment regimens, and efficient clinical decision making. But many of the advanced machine learning and deep learning models are black-box systems, and healthcare professionals find it difficult to understand the logic behind their predictions. This opacity hinders the adoption of intelligent systems in clinical settings where trust and accountability are a must. In this review paper we compare the main interpretability techniques that have been used in clinical decision support systems. These techniques include Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), saliency maps, Gradient-weighted Class Activation Mapping (Grad-CAM), attention mechanisms, and decision trees, among others. We performed a systematic literature review to evaluate these techniques based on interpretability, computational complexity, scalability, transparency, and clinical relevance. A systematic literature review was performed to evaluate the techniques in terms of interpretability, computational complexity, scalability, transparency and clinical relevance. The analysis shows that SHAP provides complete local and global explanations, while LIME provides computationally efficient local interpretations. Visualisation based methods such as Grad-CAM and saliency maps are especially useful for medical image analysis, while attention mechanisms are suitable for sequential healthcare data. The study concludes that explainable artificial intelligence improves trust, reliability, and accountability in healthcare systems and is a prerequisite for successful integration of intelligent technologies into clinical practice.
Keywords: machine learning; clinical decision support systems; Explainable Artificial Intelligence; Healthcare Analytics; interpretability
Riya Jacob K· International Journal of Tec...· 0 citations
Explainable Artificial Intelligence (XAI) has emerged as a critical enabler for the adoption of machine learning models in high-stakes domains such as healthcare. While significant progress has been made in XAI for computer vision and natural language processing, tabular data—the predominant format of electronic health records—presents unique challenges and opportunities. This systematic review provides a comprehensive analysis of XAI methods specifically applied to tabular healthcare data for classification tasks. We examine 21 primary studies published between 2020 and the first half of 2026, covering three complementary perspectives: (1) intrinsically interpretable models, (2) post-hoc methods including LIME, SHAP, and their variants, and (3) evaluation frameworks that assess both model-centered fidelity and human-centered clinical alignment. Our analysis reveals that SHAP remains the dominant post-hoc method, achieving strong model fidelity but showing inconsistent alignment with clinical expert reasoning. Key findings include the significant impact of class imbalance on explanation consistency, the importance of clinician-centered evaluation, and the emergence of hybrid approaches integrating XAI with generative AI and transfer learning. We identify critical gaps, including limited adoption of XAI in AutoML pipelines, lack of standardized evaluation metrics, and predominance of single-institution validation studies.
Angelower Santana-Velásquez, M. B. Salazar-Sánchez· Computers· 0 citations
The increasing integration of Artificial Intelligence (AI) into healthcare has transformed Clinical Decision Support Systems (CDSS) from rule-based advisory platforms into intelligent systems capable of diagnosing diseases, predicting clinical outcomes, recommending treatments, and optimizing healthcare workflows. Despite remarkable improvements in predictive performance through deep learning, ensemble learning, and generative artificial intelligence, the widespread clinical adoption of AI remains constrained by the limited transparency of complex machine learning models. Most high-performing AI algorithms function as "black-box" systems, providing highly accurate predictions while offering minimal explanation regarding the reasoning behind clinical recommendations. This lack of interpretability raises significant concerns regarding physician trust, patient safety, accountability, regulatory compliance, and ethical responsibility. Explainable Artificial Intelligence (XAI) has consequently emerged as a fundamental research direction aimed at improving transparency without substantially compromising predictive performance.
This review critically examines the role of Explainable Artificial Intelligence in developing trustworthy Clinical Decision Support Systems by synthesizing recent advances in artificial intelligence architectures, trustworthy computing principles, healthcare automation, cloud intelligence, workflow optimization, cybersecurity, and distributed system reliability. The review develops a comprehensive conceptual framework integrating explainability, clinical validation, fairness, privacy preservation, workflow automation, and governance into a unified trust model for intelligent healthcare environments. Existing research demonstrates that explainability improves physician confidence, facilitates regulatory acceptance, enhances diagnostic validation, and enables collaborative human-AI decision making. Simultaneously, emerging technologies including federated learning, digital twins, cloud intelligence, workflow automation, and real-time monitoring significantly strengthen scalability and operational resilience within healthcare infrastructures.
Aarav Sharma· European International Journ...· 0 citations
The potential benefits of artificial intelligence (AI) in healthcare cannot be overstated, and there is a lot of potential to ensure that patients can receive optimal care through early disease detection, personalized treatment options, and more. Nonetheless, the used advanced AI models have remained largely hindered by their black-box nature, which is why they are usually called the black-box problem. Such a lack of transparency undermines trust amongst clinicians and regulatory agencies so as to restrict the effective utilization of such powerful tools practically. Explainable Artificial Intelligence (XAI) appears as a decisive way out in such an essential challenge. Increasing clarity and explanation of complex machine learning models have the direct benefits of fostering more trust, as well as enhancing diagnostic accuracy and the successful overall results of patients. The effectiveness with which XAI can provide transparent and decipherable information toward AI-derived predictions is not only a technical contribution, but a necessary match with demands of ethical and clinical concerns in an area where decisions have significant implications. This means that the XAI capacity will become a rising need in a regulatory and ethical Trias handled and measured in an environment where the outcomes of decisions have great implications on the outcomes of patients. This report is an account of a framework through XAI to incorporate various health data sources such as electronic health records, medical imaging, laboratory reports, and wearable sensor information, which can be integrated in the context of achieving higher predictive performance in disease prediction and treatment stratification, as well as decision-making transparency.
M. Aparna, S. Lahane, Dr. Bharti A. Dixit· Journal of Intelligent Decis...· 0 citations
The smart healthcare systems are transforming disease diagnosis by using robust computational technology, enabling timely, accurate, and customized clinical decision-making. Explainable Artificial Intelligence (XAI) has been introduced as a promising way to enhance the transparency, interpretability, and trustworthiness of artificial intelligence (AI) models, while Quantum Computing (QC) offers unmatched computational capacity to tackle complex healthcare optimization and machine learning (ML) problems. The convergence of XAI and QC can also considerably improve disease prediction through the integration of interpretable decision support and rapid data processing and optimization. This paper provides a short literature survey on the roles of XAI and QC in smart healthcare systems for disease diagnosis. It includes advanced AI methods like deep learning (DL) and machine learning (ML) models, along with top QC tools such as Qiskit, PennyLane, Cirq, and TensorFlow Quantum. It encompasses explainability techniques such as SHAP, LIME, and Grad-CAM, which are regarded as some of the most sophisticated in the world. The survey also discusses the use of these technologies in the prediction and diagnosis of diseases such as cancer, cardiovascular diseases, diabetes, neurological diseases, and infectious diseases. The paper provides a comparative examination of existing approaches, applications in the real world of healthcare, issues that are currently being faced, and future research priorities. The review suggests that quantum-assisted XAI is in its infancy but has immense potential to design intelligent, transparent, and efficient healthcare systems that can help promote reliable disease prediction and precision therapy. The insights provided in this study present a comprehensive understanding to the researchers and healthcare practitioners about emerging trends, research gaps, and feasible directions for future smart healthcare applications.
Abasaheb Choure Kulbhushan, Vyawahare Dr. H.R.· International Journal of Inn...· 0 citations
The development of AI models in healthcare AI is hampered by a central dilemma of improving both requirements of performance and interpretability in healthcare systems. Some AI models (e.g., “XGBoost (eXtreme Gradient Boosting)”) offer remarkable accuracy, but their predictions are difficult to explain to clinicians for treatment validation. The interpretability of AI models in healthcare is crucial to meet regulatory constraints (e.g., General Data Protection Regulation (GDPR), Health Insurance Portability and Accountability Act (HIPAA)), which mandate traceability of automated decisions. This paradox is compounded by the limitations of existing explainability methods (SHAP, LIME), which suffer from instability and often produce explanations that are too technical for clinical workflows. The central problem, therefore, is to design a methodology that preserves predictive effectiveness while meeting the practical needs of clinical environments. We design an ontology-based healthcare model to improve both attributes of performance and interpretability.