QuPCG: Quantum Convolutional Neural Network for Detecting Abnormal Patterns in PCG Signals

2025-11-04

AI Summary

To address the challenge of early detection of S3 heart sounds and murmurs in phonocardiogram (PCG) signals, this paper proposes the first hybrid quantum-classical convolutional neural network (QCNN) tailored for bioacoustic signals. Methodologically, one-dimensional PCG signals are transformed via wavelet analysis and mapped onto 8×8 time-frequency images using adaptive thresholding; subsequent feature encoding and classification are performed on a shallow quantum circuit with only eight qubits. The key contributions include: (i) the first application of QCNNs to cardiac anomaly detection, and (ii) efficient modeling of physiological signal time-frequency correlations using minimal quantum resources. Evaluated on the HLS-CMDS dataset, the model achieves 93.33% test accuracy and 97.14% training accuracy, demonstrating quantum representations’ heightened sensitivity to subtle pathological patterns. This work establishes a novel paradigm for resource-efficient quantum-enabled medical diagnostics.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Early identification of abnormal physiological patterns is essential for the timely detection of cardiac disease. This work introduces a hybrid quantum-classical convolutional neural network (QCNN) designed to classify S3 and murmur abnormalities in heart sound signals. The approach transforms one-dimensional phonocardiogram (PCG) signals into compact two-dimensional images through a combination of wavelet feature extraction and adaptive threshold compression methods. We compress the cardiac-sound patterns into an 8-pixel image so that only 8 qubits are needed for the quantum stage. Preliminary results on the HLS-CMDS dataset demonstrate 93.33% classification accuracy on the test set and 97.14% on the train set, suggesting that quantum models can efficiently capture temporal-spectral correlations in biomedical signals. To our knowledge, this is the first application of a QCNN algorithm for bioacoustic signal processing. The proposed method represents an early step toward quantum-enhanced diagnostic systems for resource-constrained healthcare environments.

Problem

• Classifying S3 and murmur abnormalities in heart sound signals
• Transforming PCG signals into compressed images for quantum processing
• Developing quantum-enhanced diagnostic systems for healthcare environments

Innovation

• Hybrid quantum-classical CNN for heart sound classification
• Wavelet and compression convert PCG to 8-pixel images
• Quantum stage uses only 8 qubits for processing