Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease

2026-04-15

AI Summary

This study addresses the high sensitivity of hybrid quantum neural network (HQNN) performance in chronic kidney disease diagnosis to design choices by systematically evaluating 625 configuration combinations. These encompass five data encoding schemes (e.g., IQP), entanglement architectures (e.g., Ring), measurement strategies, and sampling shots, with impacts assessed via 10-fold stratified cross-validation. The analysis reveals non-trivial interaction effects between encoding methods and circuit architectures, demonstrating that compact HQNNs paired with appropriate encodings achieve an optimal trade-off among accuracy, robustness, and computational efficiency. The best-performing configuration leads across multiple metrics—including accuracy, AUC, F1-score, and a composite score—thereby validating the practical potential of lightweight HQNNs and offering actionable design principles for quantum-enhanced medical diagnostics.

Technology Category

• Machine Learning: Quantum Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Hybrid Quantum Neural Networks (HQNNs) have recently emerged as a promising paradigm for near-term quantum machine learning. However, their practical performance strongly depends on design choices such as classical-to-quantum data encoding, quantum circuit architecture, measurement strategy and shots. In this paper, we present a comprehensive design space exploration of HQNNs for Chronic Kidney Disease (CKD) diagnosis. Using a carefully curated and preprocessed clinical dataset, we benchmark 625 different HQNN models obtained by combining five encoding schemes, five entanglement architectures, five measurement strategies, and five different shot settings. To ensure fair and robust evaluation, all models are trained using 10-fold stratified cross-validation and assessed on a test set using a comprehensive set of metrics, including accuracy, area under the curve (AUC), F1-score, and a composite performance score. Our results reveal strong and non-trivial interactions between encoding choices and circuit architectures, showing that high performance does not necessarily require large parameter counts or complex circuits. In particular, we find that compact architectures combined with appropriate encodings (e.g., IQP with Ring entanglement) can achieve the best trade-off between accuracy, robustness, and efficiency. Beyond absolute performance analysis, we also provide actionable insights into how different design dimensions influence learning behavior in HQNNs.

Problem

• Hybrid Quantum Neural Networks
• Chronic Kidney Disease
• Design Space Exploration
• Quantum Machine Learning
• Model Performance

Innovation

• Hybrid Quantum Neural Networks
• Design Space Exploration
• Quantum Circuit Architecture
• Data Encoding
• Chronic Kidney Disease