Lung cancer screening with low-dose chest computed tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based cell-free DNA (cfDNA) biomarkers offer a complementary approach, although early detection remains difficult because of lung cancer heterogeneity and high-dimensional, nonlinear molecular signals. We evaluated quantum-classical hybrid machine learning for lung cancer detection using DNA fragmentomics and DNA methylation. After feature selection, models were trained using 20- and 40-feature subsets. Features were encoded into quantum Hilbert space using angle and dense-angle feature maps with multiple entanglement strategies. Fidelity-based quantum kernels were computed with exact statevector simulation and integrated with precomputed-kernel SVM and kernel-PCA logistic regression and compared with an SVM model trained on the original features. This framework enabled systematic evaluation of how encoding and entanglement design affect classification. Across repeated held-out evaluations, quantum-kernel models achieved competitive performance on both datasets. For fragmentomics, several 20-feature configurations improved AUC relative to a classical SVM baseline, suggesting effective capture of nonlinear cfDNA fragmentation structure. For methylation, the classical SVM achieved the highest AUC, although selected quantum models remained competitive and improved specificity in some cases. Increasing features from 20 to 40 did not consistently improve performance and often increased variability. Overall, these results support quantum kernel methods as a promising approach for cfDNA-based lung cancer detection.
Lung cancer screening with low-dose chest computed tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based cell-free DNA (cfDNA) biomarkers offer a complementary approach, although early detection remains difficult because of lung cancer heterogeneity and high-dimensional, nonlinear molecular signals. We evaluated quantum-classical hybrid machine learning for lung cancer detection using DNA fragmentomics and DNA methylation. After feature selection, models were trained using 20- and 40-feature subsets. Features were encoded into quantum Hilbert space using angle and dense-angle feature maps with multiple entanglement strategies. Fidelity-based quantum kernels were computed with exact statevector simulation and integrated with precomputed-kernel SVM and kernel-PCA logistic regression and compared with an SVM model trained on the original features. This framework enabled systematic evaluation of how encoding and entanglement design affect classification. Across repeated held-out evaluations, quantum-kernel models achieved competitive performance on both datasets. For fragmentomics, several 20-feature configurations improved AUC relative to a classical SVM baseline, suggesting effective capture of nonlinear cfDNA fragmentation structure. For methylation, the classical SVM achieved the highest AUC, although selected quantum models remained competitive and improved specificity in some cases. Increasing features from 20 to 40 did not consistently improve performance and often increased variability. Overall, these results support quantum kernel methods as a promising approach for cfDNA-based lung cancer detection.
Subtyping of lung cancer is crucial for individualized treatment and optimizing outcomes. Computational modeling allows data analysis over large scales, which helps in making precision classification in large datasets or high-dimensional datasets. Conventional machine learning methods perform well, but integration of multi-omic data (DNA, RNA, miRNA) is challenging in cancer subtyping because of high dimensionality and complex inter-omic relationships. To bypass this Quantum machine learning (QML) provides better ability to navigate high-dimensional biological data with many variables using quantum computational concepts that can identify fine patterns or small-scale patterns beyond the capability of classical approaches. Through the integration of quantum computing principles with the machine learning framework, the study highlights the improvement of computer technology. The framework shows how the system is optimized with the help of quantum principles, how it can improve accuracy, parallel processing and reducing latency. In this work, we have combined data on miRNA, RNA expression, and DNA methylation to create a complete workflow for classifying cancer. This method uses a wide variety of feature selection techniques, such as random forest-based selection, chi-square, mutual information(MI), and principal component analysis(PCA).In order to illustrate the notion of quantum advantage, we carefully compare the performance metrics of the Quantum Support Vector Classifier (QSVC) to the classical Support Vector Machine (SVM), using a ZZ feature map quantum kernel as our baseline for analysis. Using five-fold crossvalidation, we have also verified that the quantum has an advantage with consistently lower variance and higher accuracy.
The integration of classical machine learning with quantum computing has sparked a remarkable revolution, opening avenues to tackle previously insurmountable challenges in diverse fields, particularly in clinical applications. One such challenging task is to predict lung cancer with minimal clinical samples and features. The prominent objective of this proposed research is to introduce a novel Quantum Kernel Support Vector Machine (QKSVM) constructed with the Quantum Kernel Circuit (QKC) enriched with Quantum Approximation Optimization Algorithm (QAOA) embedding circuit to classify highly complex lung cancer using a minimal number of samples and minimal feature dimensions. In this context, to compare the classification performance of the transformative potential of the proposed QAOA embedding QKSVM classifier model, we implemented two other variants of the QKC leveraging Angle embedding (Angle Embedding QKSVM) and Instantaneous Quantum Polynomial embedding (IQP Embedding QKSVM). We also compared their performance with that of a classical SVM classifier. In this study, we delve into the transformative potential classification performance of the proposed QAOA Embedding-based QKSVM classifier, which is contrasted particularly in scenarios with limited sample size and feature dimensions. Our investigation reveals the quantum kernel’s superiority, even when operating with smaller datasets. This remarkable performance is attributed to the quantum models’ robustness in extracting intricate diagnosing features, enabling it to extract more pertinent insights from fewer data points. Notably, the QKSVM model trained with a significantly selected feature vector of 4-Dimensions (4D) with Principal Component Analysis (PCA) emerges as the frontrunner in lung cancer predictions, achieving an outstanding test accuracy of 94.64% and the highest area under curve (AUC) metric of 82.33%.
Background Lung cancer is a leading cause of cancer mortality, and early detection is critical for patient outcomes. Support Vector Machines (SVM) have been widely applied to diagnostic classification, but their performance can be limited in terms of sensitivity. Quantum Support Vector Machines (QSVM) offer a potential approach to improve this aspect. Methods We compared SVM and QSVM on balanced lung cancer subsets (1,000 samples each) using k-fold cross-validation. QSVM employed ZZFeatureMap and FidelityQuantumKernel for quantum feature encoding. Results QSVM achieved an average recall improvement of about 8% over classical SVM, while maintaining comparable precision and accuracy. Under a realistic 1:100 class imbalance, precision declined, highlighting challenges with highly skewed data. Conclusion QSVM shows promise for enhancing sensitivity in medical diagnostics but requires further validation on larger, heterogeneous datasets and real quantum hardware. Clinical trial number Not applicable.
Background: Classical algorithms often struggle with the high dimensionality of medical data critical for early lung cancer diagnosis. While Quantum Machine Learning (QML) offers enhanced pattern recognition capabilities, the impact of specific quantum feature encoding strategies on diagnostic accuracy remains underexplored.Methods: We evaluated Quantum Support Vector Machines (QSVM) using a dataset of 309 lung cancer patients, divided into six balanced subsets to mitigate class imbalance. Models were implemented on a qasm simulator, comparing three encoding strategies: ZFeatureMap, ZZFeatureMap, and PauliFeatureMap. Performance was assessed using standard classification metrics.Results: The choice of feature map significantly influenced model efficacy. The PauliFeatureMap outperformed other kernels, achieving 100% classification accuracy in three of the six subsets, whereas ZFeatureMap and ZZFeatureMap yielded lower predictive consistency.Conclusion: Quantum feature map selection is a decisive factor in QSVM performance. Specifically, the PauliFeatureMap demonstrates high separability for medical data, highlighting the potential of optimized quantum kernels to improve diagnostic precision.
Abstract In this study, we compare the performance of classical Support Vector Machines (SVM) and Quantum Support Vector Machines (QSVM) on binary classification tasks, using 149 balanced datasets derived from a lung cancer diagnosis dataset. Each dataset consists of 120 samples and 12 features. Our primary objective is to evaluate whether QSVM provides measurable advantages over SVM, particularly in low-performing scenarios. To this end, we identified the 15 datasets where classical SVM exhibited the lowest F1-scores and conducted a focused comparative analysis. Results show that, in these challenging cases, QSVM achieved an average recall improvement of 99% over SVM, without compromising precision. This substantial gain in recall also led to a corresponding 48% increase in F1-score, on average. Statistical analysis using a normality test followed by a paired t-test confirmed the significance of these results. These findings suggest that QSVM can serve as a valuable alternative in situations where classical models struggle, especially when high recall is critical for early cancer detection.
Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris(100%)and Wine(92%). All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.