Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is paramount. We propose a new solution to this challenge: an explainable AI framework based on our comparative study with Quantum Boltzmann Machines (QBMs) and Classical Boltzmann Machines (CBMs). We leverage principles of quantum computing within classical machine learning to provide substantive transparency around decision-making. The design involves training both models on a binarised and dimensionally reduced MNIST dataset, where Principal Component Analysis (PCA) is applied for preprocessing. For interpretability, we employ gradient-based saliency maps in QBMs and SHAP (SHapley Additive exPlanations) in CBMs to evaluate feature attributions.QBMs deploy hybrid quantum-classical circuits with strongly entangling layers, allowing for richer latent representations, whereas CBMs serve as a classical baseline that utilises contrastive divergence. Along the way, we found that QBMs outperformed CBMs on classification accuracy (83.5% vs. 54%) and had more concentrated distributions in feature attributions as quantified by entropy (1.27 vs. 1.39). In other words, QBMs not only produced better predictive performance than CBMs, but they also provided clearer identification of "active ingredient" or the most important features behind model predictions. To conclude, our results illustrate that quantum-classical hybrid models can display improvements in both accuracy and interpretability, which leads us toward more trustworthy and explainable AI systems.
Journal reference
Proceedings of the 2025 9th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)
Accepted and published in IEEE 2025. This is the authors manuscript version; final version available at IEEE Xplore: https://ieeexplore.ieee.org/document/11318441
Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is paramount. We propose a new solution to this challenge: an explainable AI framework based on our comparative study with Quantum Boltzmann Machines (QBMs) and Classical Boltzmann Machines (CBMs). We leverage principles of quantum computing within classical machine learning to provide substantive transparency around decision-making. The design involves training both models on a binarised and dimensionally reduced MNIST dataset, where Principal Component Analysis (PCA) is applied for preprocessing. For interpretability, we employ gradient-based saliency maps in QBMs and SHAP (SHapley Additive exPlanations) in CBMs to evaluate feature attributions.QBMs deploy hybrid quantum-classical circuits with strongly entangling layers, allowing for richer latent representations, whereas CBMs serve as a classical baseline that utilises contrastive divergence. Along the way, we found that QBMs outperformed CBMs on classification accuracy (83.5% vs. 54%) and had more concentrated distributions in feature attributions as quantified by entropy (1.27 vs. 1.39). In other words, QBMs not only produced better predictive performance than CBMs, but they also provided clearer identification of "active ingredient" or the most important features behind model predictions. To conclude, our results illustrate that quantum-classical hybrid models can display improvements in both accuracy and interpretability, which leads us toward more trustworthy and explainable AI systems.
This research paper explores the explainability of decision-making in hybrid quantum–classical classification models. Quantum Machine Learning (QML) combines the power of quantum computing with classical machine learning techniques to solve complex computational problems. However, understanding how these hybrid models make decisions remains a significant challenge. The study focuses on analyzing hybrid quantum–classical architectures and evaluating methods that improve the interpretability of their predictions. Techniques from Explainable Artificial Intelligence (XAI) are applied to investigate the internal decision-making processes of the models. The research also compares classical machine learning approaches with quantum-enhanced models to understand their performance and transparency. The results demonstrate that explainability techniques can help researchers better interpret model predictions, identify important features, and improve trust in hybrid quantum–classical systems. This work contributes to the development of transparent and reliable quantum machine learning applications in areas such as healthcare, finance, and data analytics.
The rapid advancement of Artificial Intelligence (AI) has heightened concerns about the opacity of decision-making processes in complex models, particularly deep neural networks. This research explores a novel paradigm that integrates quantum computing principles into Explainable AI (XAI) to enhance interpretability without compromising predictive accuracy. The study introduces a Quantum-inspired Interpretable Model (QIIM) framework that leverages Hilbert space embeddings, unitary transformations, and operator-based learning to represent knowledge in a mathematically transparent form. The proposed model computes interpretability through the expectation values of observable operators, enabling the decomposition of decisions into quantifiable, human-understandable components. To capture hierarchical relationships, a Tensor Network Interpretable Model (TNIM) is further developed, offering scalable insights into complex dependencies among features. Experimental evaluations—performed on benchmark datasets for decision-making tasks—demonstrate that the quantum-inspired models achieve competitive accuracy while significantly improving local and global interpretability metrics compared to classical XAI techniques. The findings underscore the potential of quantum formalism as a new foundation for transparent AI systems, bridging the gap between computational efficiency and explainability. This study contributes to both theoretical understanding and practical advancement in interpretable machine learning, paving the way for ethically aligned, transparent, and human-trustworthy AI-driven decision support systems.
The integration of Quantum Computing with Artificial Intelligence (AI) presents a transformative opportunity for advanced medical imaging analysis. This paper proposes an Explainable Quantum AI (XQAI) framework for radiology decision support systems, aimed at enhancing diagnostic accuracy while ensuring interpretability of results. The approach leverages quantum kernel-based feature extraction to capture complex spatial–spectral patterns in MRI, CT, and PET scans, enabling superior detection of subtle anomalies. A hybrid quantum- classical deep learning model is employed, where quantum circuits perform high-dimensional feature mapping, and classical neural networks execute classification tasks. To address the "black-box" challenge in AI-assisted diagnosis, the framework incorporates quantum explainability modules using measurement-driven saliency mapping and Shapley value–based feature attribution. This dual- layer explainability provides radiologists with both a quantum- informed feature importance ranking and a visual heatmap overlay on the medical image. Experimental evaluation on publicly available medical imaging datasets demonstrates improved detection sensitivity (7.3%) and diagnostic confidence compared to conventional deep learning approaches, while reducing model opacity. The proposed XQAI system offers a pathway towards trustworthy, high-performance, and clinically deployable quantum-assisted diagnostic tools in radiology.
Abstract As machine learning grows increasingly complex due to big data and deep learning, model explainability has become essential to fostering user trust. Quantum machine learning (QML) has emerged as a promising field, leveraging quantum computing to enhance classical machine learning methods, particularly through quantum representation learning (QRL). QRL aims to provide more efficient and powerful machine learning capabilities on noisy intermediate-scale quantum (NISQ) devices. However, interpreting QRL models poses significant challenges due to the reliance on quantum gate-based parameterized circuits, which, while analogous to classical neural network layers, operate in the quantum domain. To address these challenges, we propose an explainable QRL framework combining a quantum autoencoder (QAE) with a variational quantum classifier (VQC) and incorporating theoretical and empirical explainability for image data. Our dual approach enhances model interpretability by integrating visual explanations via local interpretable model-agnostic explanations (LIME) and analytical insights using Shapley Additive Explanations (SHAP). These complementary methods provide a deeper understanding of the model’s decision-making process based on prediction outcomes. Experimental evaluations on simulators and superconducting quantum hardware validate the effectiveness of the proposed framework for classification tasks, underscoring the importance of explainable representation learning in advancing QML towards more transparent and reliable applications.
Disease hazard prediction has been transformed by the use of artificial intelligence in healthcare; however, there are still problems with striking a balance between interpretability and predictive routine, mostly when working with complex, high-dimensional clinical data. To improve the precision, scalability, and transparency of disease risk prediction, this work presents a novel Quantum-Enabled Explainable AI (QXAI) system that syndicates explainable machine learning with quantum computing. Through the use of quantum algorithms, explicitly quantum kernel methods and quantum-enhanced feature selection, the suggested system achieves huge electronic health record (EHR) datasets efficiently while addressing problems with non-linearity and data narrowness. This work uses explainable AI methods like SHAP and counterfactual reasoning to guarantee interpretability, allowing doctors to understand the reasoning behind predictions. Real-world medical datasets are used for a thorough evaluation, which shows that the QXAI system finishes better than traditional baselines in terms of prediction accuracy, model robustness, and explanation reliability. In the end, this paper places the foundation for the implementation of reliable, quantum-assisted decision support systems in medical practice, which will lead to more personalized, reasonable, and knowledgeable healthcare.
Early and accurate prediction of cardiovascular disease is essential to improve patient outcomes and reduce healthcare costs. This research presents a hybrid classical–quantum machine learning framework for heart disease prediction using the Cleveland dataset. The proposed pipeline integrates advanced feature engineering, bio-inspired optimization, and quantum-inspired learning to improve classification performance and interpretability. The system applies multiple feature selection techniques followed by a hybrid feature fusion strategy. Orthogonal Component Analysis is then used for dimensionality transformation, while quantum-inspired feature mapping simulates quantum state coding. A feature selection mechanism based on a Genetic Algorithm optimizes the subset of features. Classical and quantum machine learning models are evaluated, including Random Forest, Gradient Boosting, K-Nearest Neighbors, Logistic Regression, Quantum Support Vector Classifier, Variational Quantum Classifier, Quantum KNN, and Quantum Neural Networks. Model performance is evaluated using accuracy metrics. To ensure transparency and trustworthiness, explainable AI techniques such as SHAP, LIME and DiCE are integrated to provide local and global interpretability of predictions. Experimental results demonstrate that the proposed hybrid framework improves predictive performance by achieving 90% accuracy compared to traditional machine learning approaches, while maintaining model explainability. The model achieved an overall accuracy of 90%, indicating strong predictive capability in cardiovascular disease risk classification. A detailed analysis of class-wise performance shows that for Class 0, the model obtained a precision of 0.85, a recall of 0.97, and an F1-score of 0.90, demonstrating excellent ability to correctly identify negative cases with minimal false negatives. For Class 1, the model achieved a precision of 0.96, a recall of 0.84, and an F1-score of 0.90, indicating high confidence in positive predictions, though with slightly lower recall compared to Class 0. This study highlights the potential of combining classical feature engineering, evolutionary optimization and quantum-inspired learning for next-generation medical decision support systems. The integration of quantum-inspired techniques also provides a promising direction for improving computational efficiency and model robustness in healthcare analytics. The findings suggest that hybrid classical–quantum learning approaches can support clinicians in making faster and more reliable diagnostic decisions.