@Article{cmc.2025.065287,
AUTHOR = {Prasanna Kottapalle, Tan Kuan Tak, Pravin Ramdas Kshirsagar, Gopichand Ginnela, Vijaya Krishna Akula},
TITLE = {QHF-CS: Quantum-Enhanced Heart Failure Prediction Using Quantum CNN with Optimized Feature Qubit Selection with Cuckoo Search in Skewed Clinical Data},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {84},
YEAR = {2025},
NUMBER = {2},
PAGES = {3857--3892},
URL = {http://www.techscience.com/cmc/v84n2/62910},
ISSN = {1546-2226},
ABSTRACT = {Heart failure prediction is crucial as cardiovascular diseases become the leading cause of death worldwide, exacerbated by the COVID-19 pandemic. Age, cholesterol, and blood pressure datasets are becoming inadequate because they cannot capture the complexity of emerging health indicators. These high-dimensional and heterogeneous datasets make traditional machine learning methods difficult, and Skewness and other new biomarkers and psychosocial factors bias the model’s heart health prediction across diverse patient profiles. Modern medical datasets’ complexity and high dimensionality challenge traditional prediction models like Support Vector Machines and Decision Trees. Quantum approaches include QSVM, QkNN, QDT, and others. These Constraints drove research. The “QHF-CS: Quantum-Enhanced Heart Failure Prediction using Quantum CNN with Optimized Feature Qubit Selection with Cuckoo Search in Skewed Clinical Data” system was developed in this research. This novel system leverages a Quantum Convolutional Neural Network (QCNN)-based quantum circuit, enhanced by meta-heuristic algorithms—Cuckoo Search Optimization (CSO), Artificial Bee Colony (ABC), and Particle Swarm Optimization (PSO)—for feature qubit selection. Among these, CSO demonstrated superior performance by consistently identifying the most optimal and least skewed feature subsets, which were then encoded into quantum states for circuit construction. By integrating advanced quantum circuit feature maps like ZZFeatureMap, RealAmplitudes, and EfficientSU2, the QHF-CS model efficiently processes complex, high-dimensional data, capturing intricate patterns that classical models overlook. The QHF-CS model improves precision, recall, F1-score, and accuracy to 0.94, 0.95, 0.94, and 0.94. Quantum computing could revolutionize heart failure diagnostics by improving model accuracy and computational efficiency, enabling complex healthcare diagnostic breakthroughs.},
DOI = {10.32604/cmc.2025.065287}
}