Early diagnosis of lung cancer and reliable decision support are crucial steps since this is a leading cause of cancer-related mortality worldwide. This research aims to build an approach using quantum-assisted capacity that can infer lung cancer from a limited amount of patient data. To do so, this research starts with a dataset containing 309 patient records, which is augmented and balanced to 540 patient records. This dataset has 16 attributes of symptom and risk-based lung cancer factors. Following preprocessing on the dataset, this study uses a quantum method named quadratic unconstrained binary optimization (QUBO) to select the relevant features of the dataset. Three classifiers, quantum support vector machine (QSVM), quantum k-nearest neighbor (QKNN), and quantum boosting (QBoost), are then trained and tested on the processed dataset to identify lung cancer. These classifiers are examined using different frameworks of circuit and annealing-based quantum techniques. Only 108 balance samples are used during training the classifiers to ensure the learning capability of the quantum method from limited data. To safeguard against overfitting and underfitting due to a lack of data, the remaining 432 samples are evaluated to estimate prediction error. All experiments are done using cross-validation. The final results demonstrate that the QSVM by D-Wave framework achieves the best performance with an accuracy of 94.31% in simulation and 91.90% in a real D-Wave quantum computer. The findings of this work show a path for applying quantum computing to support healthcare decision-making when data availability is often limited.
Early diagnosis of lung cancer and reliable decision support are crucial steps since this is a leading cause of cancer-related mortality worldwide. This research aims to build an approach using quantum-assisted capacity that can infer lung cancer from a limited amount of patient data. To do so, this research starts with a dataset containing 309 patient records, which is augmented and balanced to 540 patient records. This dataset has 16 attributes of symptom and risk-based lung cancer factors. Following preprocessing on the dataset, this study uses a quantum method named quadratic unconstrained binary optimization (QUBO) to select the relevant features of the dataset. Three classifiers, quantum support vector machine (QSVM), quantum k-nearest neighbor (QKNN), and quantum boosting (QBoost), are then trained and tested on the processed dataset to identify lung cancer. These classifiers are examined using different frameworks of circuit and annealing-based quantum techniques. Only 108 balance samples are used during training the classifiers to ensure the learning capability of the quantum method from limited data. To safeguard against overfitting and underfitting due to a lack of data, the remaining 432 samples are evaluated to estimate prediction error. All experiments are done using cross-validation. The final results demonstrate that the QSVM by D-Wave framework achieves the best performance with an accuracy of 94.31% in simulation and 91.90% in a real D-Wave quantum computer. The findings of this work show a path for applying quantum computing to support healthcare decision-making when data availability is often limited.
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.
In recent years, quantum machine learning has emerged as a promising intersection between quantum physics and artificial intelligence, particularly in domains requiring advanced pattern recognition such as healthcare. This study investigates the effectiveness of Quantum Support Vector Machines (QSVM), which leverage quantum mechanical phenomena like superposition and entanglement to construct high-dimensional Hilbert spaces for data classification. Focusing on lung cancer diagnosis, a concrete and critical healthcare application, we analyze how different quantum feature maps influence classification performance. Using a real-world dataset of 309 patient records with significant class imbalance (39 non-cancer vs. 270 cancer cases), we constructed six balanced subsets for robust evaluation. QSVM models were implemented using Qiskit and executed on the qasm simulator, employing three distinct quantum feature maps: ZFeatureMap, ZZFeatureMap, and PauliFeatureMap. Performance was assessed using accuracy, precision, recall, specificity, and F1-score. Results show that the PauliFeatureMap consistently outperformed the others, achieving perfect classification in three subsets and strong performance overall. These findings demonstrate how quantum computational principles can be harnessed to enhance diagnostic capabilities, reinforcing the importance of physics-based modeling in emerging AI applications within healthcare.
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.
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.
Ovarian cancer remains one of the leading causes of cancer-related mortality among women worldwide, largely because most cases are diagnosed at advanced stages. Current diagnostic tools and classical machine learning models often show limited sensitivity and specificity, particularly when applied to the complex, high-dimensional datasets required for accurate prediction. These limitations highlight the need for more powerful computational approaches capable of extracting subtle diagnostic patterns. The aim of this study is to enhance the accuracy and efficiency of ovarian cancer diagnosis by using quantum-inspired machine learning approach such as Quantum Support Vector Machines (QSVMs). The study utilized QSVMs to analyse clinical and genomic datasets, leveraging quantum mechanics principles like superposition and entanglement to process data more effectively than traditional machine learning models. The QSVM model was developed, trained, and evaluated using performance metrics such as accuracy, sensitivity, specificity, and processing efficiency. The results demonstrated that QSVMs achieved a diagnostic accuracy of 92%, outperforming traditional support vector machines and other classical models. Additionally, the processing time for diagnosis was reduced from 45 minutes to 20 minutes, providing a faster and more reliable workflow. The QSVMs also excelled in analysing multi-omics data, enabling the identification of early-stage ovarian cancer biomarkers and supporting personalized treatment strategies. In conclusion, this study demonstrates the potential of QSVMs to transform ovarian cancer diagnostics by addressing key limitations of conventional methods. The findings underscore the importance of adopting quantum-inspired machine learning in medical applications and encourage further exploration of these advanced algorithms in improving healthcare outcomes.
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%.