Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Advances in computational intelligence and robotics book series

Quantum Explainable AI-Integrating Interpretability With Quantum Intelligence Using Information-Theoretic Approaches

S. Bharathi, P. Prakasam

Published Nov 5, 2026• 0 citations
Publisher

Abstract

We introduce an Information-Theoretic Quantum Explainable Artificial Intelligence (IT-QXAI) framework to incorporate explainability in quantum machine learning models. The integration of quantum computing and AI can bring significant computational benefits. But it brings new challenges for interpretability, especially in critical applications such as health, cybersecurity, and vehicular fog computing (VFC). It uses entropy, quantum mutual information and quantum relative entropy to measure uncertainty, and to capture the interactions between features of quantum models. An architecture and taxonomy of QXAI are proposed to enable reliable explanations. VFC settings demonstrate IT-QXAI's potential to support smart task offloading, resource management, and decision-making in dynamic environments. The selection of information-theoretic measures ensures explanations are consistent with quantum processes. Challenges such as quantum noise, scalability, and the lack of evaluation metrics are discussed, along with research opportunities for scalable, user-friendly explainability techniques.

DOI
10.4018/979-8-2600-0482-1.ch009

Related papers

Quantum Explainable AI

Tushar Tushar, Pooja Jaiswal, Shyam Sundar

Quantum Explainable Artificial Intelligence (QXAI) is an interdisciplinary and rapidly developing branch of quantum computing that integrates the concepts of XAI with the principles of quantum computing, to make hybrid quantum-classical systems more transparent, reliable, and interpretable. In this chapter the principles of QXAI are derived from quantum information theory, entropy, fidelity analysis and computational complexity modeling. It introduces the QuXAI framework and the Q-MEDLEY explainer to provide feature attribution for hybrid quantum-classical machine learning models and maintain quantum transformations. The chapter explores a more in-depth analysis of noisy quantum states with the help of entropy and fidelity analysis and quantum simulation, noise modeling, and fuzzy c means clustering. Moreover, it presents interpretable quantum-inspired models, such as QIIM and TNIM, and proposes the Quantum Attention Network to facilitate the analysis of quantum complexity in the era of AI-enhanced quantum intelligent systems, scaling up and making them transparent and responsible.

Advances in computational intelligence and robotics book series•Nov 5, 2026•0 citations

Quantum Computing for Explainable AI: Developing Quantum-inspired Interpretable Models for Complex Decision-making Systems

Chidera Onyeka Agu

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.

British Journal of Computer Networking and Information Technology•Dec 3, 2025•1 citation

Design and Evaluation of a Quantum-Enabled Explainable AI System for Disease Risk Prediction in Healthcare

Dattatray Raghunath Kale, Panil Jain, Tejal Deshpande +3 more

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.

IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS)•Oct 30, 2025•3 citations

Explainability of Decision-Making in Hybrid Quantum-Classical Classification Models

Sayali Ramesh Kote

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.

•Mar 9, 2026•0 citations

Explainable Quantum Artificial Intelligence for Enhanced Radiology Decision Support

Sundaram K. Meenakshi, Saraswathi V, Malathy M +1 more

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.

IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM)•Oct 29, 2025•0 citations

A Novel Approach to Explainable AI with Quantized Active Ingredients in Decision Making

A. M. A. S. D. Alagiyawanna, Asoka Karunananda, Thushari Silva +1 more

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.

cs.LGCross-listedarXiv:2601.08733•SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)•Jan 14, 2026•0 citations
We introduce an Information-Theoretic Quantum Explainable Artificial Intelligence (IT-QXAI) framework to incorporate explainability in quantum machine learning models. The integration of quantum computing and AI can bring significant computational benefits. But it brings new challenges for interpretability, especially in critical applications such as health, cybersecurity, and vehicular fog computing (VFC). It uses entropy, quantum mutual information and quantum relative entropy to measure uncertainty, and to capture the interactions between features of quantum models. An architecture and taxonomy of QXAI are proposed to enable reliable explanations. VFC settings demonstrate IT-QXAI's potential to support smart task offloading, resource management, and decision-making in dynamic environments. The selection of information-theoretic measures ensures explanations are consistent with quantum processes. Challenges such as quantum noise, scalability, and the lack of evaluation metrics are discussed, along with research opportunities for scalable, user-friendly explainability techniques.
Quantum Explainable Artificial Intelligence (QXAI) is an interdisciplinary and rapidly developing branch of quantum computing that integrates the concepts of XAI with the principles of quantum computing, to make hybrid quantum-classical systems more transparent, reliable, and interpretable. In this chapter the principles of QXAI are derived from quantum information theory, entropy, fidelity analysis and computational complexity modeling. It introduces the QuXAI framework and the Q-MEDLEY explainer to provide feature attribution for hybrid quantum-classical machine learning models and maintain quantum transformations. The chapter explores a more in-depth analysis of noisy quantum states with the help of entropy and fidelity analysis and quantum simulation, noise modeling, and fuzzy c means clustering. Moreover, it presents interpretable quantum-inspired models, such as QIIM and TNIM, and proposes the Quantum Attention Network to facilitate the analysis of quantum complexity in the era of AI-enhanced quantum intelligent systems, scaling up and making them transparent and responsible.
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.
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.
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 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.
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.