BACKGROUND: Heart failure remains a critical global health issue, contributing significantly to cardiovascular disease burden and accounting for approximately 17.8 million annual deaths worldwide. Traditional diagnostic approaches face substantial limitations in early detection and intervention planning. PROBLEM: Classical machine learning models struggle with complex, high-dimensional data, class imbalances, poor categorical feature representations, and lack interpretability due to their 'black box' nature. While quantum machine learning shows potential, existing hybrid models have yet to capitalize on quantum advantages for cardiovascular diagnostics fully. SOLUTION: We propose the Kolmogorov-Arnold Classical-Quantum Dual-Channel Neural Network (KACQ-DCNN), a novel hybrid architecture that integrates KAN components with quantum circuits, enabling univariate learnable activation functions that significantly improve function approximation with reduced complexity. Our comprehensive evaluation demonstrates that the KACQ-DCNN 4-qubit 1-layered model outperforms 37 benchmark models with 92.03% accuracy and 94.77% ROC-AUC score. Ablation studies confirm a synergistic effect of classical-quantum components with KAN, improving accuracy by approximately 2% compared to MLP variants. BENEFITS: KACQ-DCNN improves heart disease detection accuracy while providing interpretable insights through model-agnostic explainability techniques like Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP). Additionally, conformal prediction techniques deliver robust uncertainty quantification, advancing the field toward more reliable, transparent, and clinically trustworthy cardiovascular diagnostic systems that facilitate timely and effective interventions.
BACKGROUND: Heart failure remains a critical global health issue, contributing significantly to cardiovascular disease burden and accounting for approximately 17.8 million annual deaths worldwide. Traditional diagnostic approaches face substantial limitations in early detection and intervention planning. PROBLEM: Classical machine learning models struggle with complex, high-dimensional data, class imbalances, poor categorical feature representations, and lack interpretability due to their 'black box' nature. While quantum machine learning shows potential, existing hybrid models have yet to capitalize on quantum advantages for cardiovascular diagnostics fully. SOLUTION: We propose the Kolmogorov-Arnold Classical-Quantum Dual-Channel Neural Network (KACQ-DCNN), a novel hybrid architecture that integrates KAN components with quantum circuits, enabling univariate learnable activation functions that significantly improve function approximation with reduced complexity. Our comprehensive evaluation demonstrates that the KACQ-DCNN 4-qubit 1-layered model outperforms 37 benchmark models with 92.03% accuracy and 94.77% ROC-AUC score. Ablation studies confirm a synergistic effect of classical-quantum components with KAN, improving accuracy by approximately 2% compared to MLP variants. BENEFITS: KACQ-DCNN improves heart disease detection accuracy while providing interpretable insights through model-agnostic explainability techniques like Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP). Additionally, conformal prediction techniques deliver robust uncertainty quantification, advancing the field toward more reliable, transparent, and clinically trustworthy cardiovascular diagnostic systems that facilitate timely and effective interventions.
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.
Cardiovascular disease has become a major public health issue as the leading cause of death. Timely and accurate detection of heart disease is critical to prevent additional harm to patients. Recent studies show that the implementation of datadriven approaches in medicine, including machine learning (ML) and deep learning (DL), significantly improves the speed and accuracy of heart disease diagnosis. This study proposes a hybrid deep learning model that integrates traditional convolutional neural networks (CNNs) with quantum computing to improve the accuracy of the prediction of cardiovascular diseases. The model uses a parameterized quantum circuit (PQC) to encode patient data, including ECG signals and cardiac images, into quantum states to extract quantum features. Quantum gates modify quantum states to extract complex and high-dimensional features that may be beyond the capabilities of conventional algorithms. A CNN uses convolutional filters to detect localized patterns, including arrhythmias and structural heart abnormalities, to diagnose cardiovascular disease. The CNN then receives the output from the PQC. Integrating quantum feature extraction with conventional deep learning improves prediction accuracy and robustness, facilitating the analysis of high-dimensional and spatially dependent data. The ability of the hybrid model to identify cardiovascular diseases in their early stages may enable faster and more accurate diagnostic results, making it an innovative tool for personalized medicine.
Abstract Cardiovascular disease (CVD) remains the leading cause of global mortality, accounting for approximately 17.9 million deaths annually. It is required that the development of sophisticated network-based predictive algorithms that can preserve the multifaceted feature interaction in the early detection of the disease and clinical decision support. This research introduces a new hybrid scheme of quantum-inspired feature interaction networks and deep neural network structures to predict CVD. We use our methodology to build a full graph of feature interactions based on ZZ-feature maps and the weight of edges is a pairwise quantum-inspired correlation between clinical features. This network-based representation is further provided to a multi-layered neural network with ensemble decision-making. Experimental validation on the UCI Cleveland Heart Disease dataset demonstrates (303 patients, 13 clinical attributes), our hybrid architecture has an accuracy of 90.5% (95% CI: 89.491.6), precision of 89.1, recall of 91.24%, F1-score of 89.9%, and ROC-AUC of 0.936, and a 5-fold stratified cross-validation. The statistical significance analysis confirms that the quantum-inspired network transformation yields statistically significant performance improvements over the baseline approaches (p < 0.01, Cohen’s d > 0.8). However, we note that control experiments isolating the ZZ-feature map contribution from the dimensionality expansion (20→40 dimensions) and ensemble effects have not been performed in the current study and are reserved for future work. The results of SHAP-based network interpretability analysis indicate that thalassemia, the major vessel count, and chest pain type are the most powerful nodes in the prediction network, which aligns with traditional cardiovascular diagnostic guidelines. The suggested framework provides a reproducible methodology, with transparent limitation reporting, that serves as a basis for network-driven clinical decision support systems and preserves paths for translating quantum hardware.
Liver disease remains a major global health concern, highlighting the need for reliable and accessible early detection methods. Although recent advances in machine learning, deep learning and quantum machine learning (QML) have introduced promising diagnostic tools, many approaches suffer from limited interpretability and inflated performance caused by data leakage or overly simplistic evaluation protocols. These constraints reduce their reliability in real-world clinical practice. This paper proposes KQML-Liver, a hybrid framework that integrates QML with Kolmogorov-Arnold Networks (KANs) to enhance predictive performance and interpretability. The architecture combines parameterized quantum circuits for expressive feature representation with KAN-based functional mappings that capture nonlinear relationships in an interpretable manner. Evaluated on the Indian Liver Patient Dataset (ILPD) under a rigorous preprocessing protocol preventing data leakage, the proposed model achieves 82% classification accuracy and 100% recall, detecting all positive cases, outperforming existing baselines while providing improved transparency in clinical predictions. These results suggest that hybrid KAN-quantum architectures offer a promising direction for interpretable AI-assisted medical diagnosis.
Cardiovascular disease remains one of the leading causes of death worldwide, making early and accurate risk prediction essential. Conventional machine learning models often struggle to handle complex medical data, resulting in limited accuracy and reduced interpretability. To address these challenges, this study presents a hybrid prediction framework that combines Quantum Machine Learning (QML) with ensemble learning techniques. Classical models such as Support Vector Classifier (SVC) and Artificial Neural Network (ANN) are used as baseline approaches. In addition, quantum models including QSVC, Variational Quantum Classifier (VQC), and Quantum Neural Network (QNN) are employed to capture complex non-linear patterns present in clinical data. To further enhance performance, a Bagging-QSVC ensemble model is proposed, improving robustness and overall classification accuracy. Interpretability is incorporated using SHAP, allowing the model’s predictions to be more transparent and easier to understand in a clinical context. Experimental results indicate that the proposed quantum ensemble achieves an accuracy of around 90%, outperforming both classical models and individual quantum models. Furthermore, a real-time user interface is developed, enabling clinicians to input patient data and receive immediate risk predictions. Overall, the system provides a reliable and interpretable solution suitable for practical clinical decision support.
Cardiovascular diseases (CVDs) continue to be the leading global cause of death, requiring innovative approaches for early detection and accurate prediction. This study explores the transformative potential of quantum-enhanced machine learning (queml) models in cardiovascular disease prediction, addressing the limitations of conventional diagnostic approaches. Using extensive datasets including the Kaggle Heart Disease Dataset of 1,190 patient records and the Cleveland/State Registry datasets, the quantum-enhanced models show superior performance over traditional machine learning approaches, with QCVNET achieving 91.73% accuracy and queml showing a 0.6% improvement in accuracy, while reducing training time from 862.5 µs to 670 µs per cycle. Key physiological parameters including diabetes indicators, LDL cholesterol, HDL cholesterol, and triglycerides were incorporated as predictive features. The IQCNN framework achieved 91% classification accuracy at a learning rate of 70%, significantly outperforming the Bi-LSTM and CNN approaches. Comparative analysis revealed exceptional AUC scores of 96.43% and 97.78% for the hybrid models, establishing quantum-enhanced machine learning as a highly effective solution for cardiovascular risk assessment and early detection systems.