Quantum machine learning models have shown potential for classification problems, but the scenarios where quantum kernels outperform the classical approach are not well understood. We take five UCI medical datasets Parkinson's, Chronic Kidney Disease, Heart disease, Breast Cancer, and Hepatitis with different sample sizes and check for quantum kernel performance. We made a complexity-based framework linking dataset characteristics including Fisher discriminant ratio, intrinsic dimensionality, and feature correlation with quantum advantage. The hepatitis dataset which has the lowest fisher ratio (0.253) of all the datasets shows a quantum advantage (+6%, p=0.12) under optimized preprocessing conditions, according to our experiments using ZZFeatureMap quantum kernels when compared to classical RBF, polynomial and linear kernels. We show that quantum kernels perform competitively on datasets with limited class separability and at small sample sizes (n<50). These results help by offering useful suggestions for practitioners choosing between quantum and classical kernel approaches for medical classification problems.
Quantum machine learning models have shown potential for classification problems, but the scenarios where quantum kernels outperform the classical approach are not well understood. We take five UCI medical datasets Parkinson's, Chronic Kidney Disease, Heart disease, Breast Cancer, and Hepatitis with different sample sizes and check for quantum kernel performance. We made a complexity-based framework linking dataset characteristics including Fisher discriminant ratio, intrinsic dimensionality, and feature correlation with quantum advantage. The hepatitis dataset which has the lowest fisher ratio (0.253) of all the datasets shows a quantum advantage (+6%, p=0.12) under optimized preprocessing conditions, according to our experiments using ZZFeatureMap quantum kernels when compared to classical RBF, polynomial and linear kernels. We show that quantum kernels perform competitively on datasets with limited class separability and at small sample sizes (n<50). These results help by offering useful suggestions for practitioners choosing between quantum and classical kernel approaches for medical classification problems.
The support vector machine algorithm with a quantum kernel estimator (QSVM-Kernel), as a leading example of a quantum machine learning technique, has undergone significant advancements. Nevertheless, its integration with classical data presents unique challenges. While quantum computers primarily interact with data in quantum states, embedding classical data into quantum states using feature mapping techniques is essential for leveraging quantum algorithms Despite the recognized importance of feature mapping, its specific impact on data classification outcomes remains largely unexplored. This study addresses this gap by comprehensively assessing the effects of various feature mapping methods on classification results, taking medical data analysis as a case study. In this study, the QSVM-Kernel method was applied to classification problems in two different and publicly available medical datasets, namely, the Wisconsin Breast Cancer (original) and The Cancer Genome Atlas (TCGA) Glioma datasets. In the QSVM-Kernel algorithm, quantum kernel matrices obtained from 9 different quantum feature maps were used. Thus, the effects of these quantum feature maps on the classification results of the QSVM-Kernel algorithm were examined in terms of both classifier performance and total execution time. As a result, in the Wisconsin Breast Cancer (original) and TCGA Glioma datasets, when Rx and Ry rotational gates were used, respectively, as feature maps in the QSVM-Kernel algorithm, the best classification performances were achieved both in terms of classification performance and total execution time. The contributions of this study are that (1) it highlights the significant impact of feature mapping techniques on medical data classification outcomes using the QSVM-Kernel algorithm, and (2) it also guides undertaking research for improved QSVM classification performance.
High-dimensional data classification -- where feature dimensionality p exceeds or approaches sample size n -- is ubiquitous in genomics, medical imaging, spectroscopy, and financial risk modelling. Quantum machine learning (QML) offers potential advantages for high-dimensional classification through quantum feature maps that implicitly operate in exponentially large Hilbert spaces, potentially capturing feature correlations inaccessible to polynomial-complexity classical kernel methods. However, identifying when and why QML provides genuine classification advantage over classical methods for high-dimensional data remains an open question, complicated by the QCCB finding (Popescu and Petrov, 2024) that quantum kernel advantages are dataset-specific. This paper proposes the Quantum High-Dimensional Classification (QHDC) framework, investigating QML advantage for five high-dimensional classification problems across three quantum model families: quantum kernel SVM (QKSVM) using parameterised ZZFeatureMap and IQPFeatureMap; quantum neural network classifier (QNNC) using LSAD-structured ansatz (Silva et al., 2024); and quantum-classical transfer learning (QCTL) using a quantum feature extractor with classical fine-tuning head. QHDC is evaluated on five datasets: genomic variant classification (p=8,442, n=284), hyperspectral remote sensing (p=200, n=10,249), drug-protein binding prediction (p=1,024, n=4,284), financial credit risk (p=84, n=28,400), and quantum chemistry energy prediction (p=48, n=2,840). QKSVM achieves the highest QML performance: AUC improvement over classical RBF-SVM of 2.4-8.4pp across five datasets, with largest gains on quantum chemistry (8.4pp) and drug- protein (6.4pp) datasets. QNNC underperforms classical baselines on three of five datasets due to barren plateau limitations at high dimensionality. QCTL achieves 4.4pp improvement on genomic classification.
Quantum-assisted machine learning approaches have become a significant area of research in the healthcare domain by offering alternative solutions to classical methods, particularly when dealing with high-dimensional and complex datasets. This study presents a comparative evaluation of the classification performance of classical Support Vector Machines (SVM) and quantum-based algorithms Quantum Support Vector Machine (QSVM) and Pegasos-QSVM on healthcare data. Experimental analyses were conducted using three distinct medical datasets related to liver disease, breast cancer, and heart failure. The results demonstrate that the QSVM model consistently achieved the highest and most stable classification accuracy. Although the Pegasos-QSVM model achieved comparable accuracy rates in certain configurations, its performance was generally more variable. Nevertheless, thanks to its lower computational cost and faster processing time, Pegasos-QSVM emerges as a promising alternative, particularly in resource-constrained environments. The findings suggest that quantum-assisted models can deliver performance levels competitive with classical approaches, particularly highlighting the effectiveness of QSVM on small- to medium-sized datasets.
The incorporation of quantum ansatz with machine learning classification models demonstrates the ability to extract patterns from data for classification tasks. However, to take the computational advantage of quantum machine learning, researchers have to deal with various constraints. In this paper, we focus on constraints like finding suitable datasets where quantum advantage is achievable and evaluating the relevance of features chosen by classical and quantum methods. Additionally, we compare quantum and classical approaches using benchmarks and estimate the computational complexity of quantum circuits to assess real-world usability. For our experimental validation, we selected the gene expression dataset, given the critical role of genetic variations in regulating physiological behavior and disease susceptibility. Through this study, we aim to improve quantum machine learning methods and provide useful insights into how they can help solve complex classification problems in different fields.
In this study, the performance of classical and quantum machine learning models was compared using the Breast Cancer dataset, which consists of diagnostic data aimed at classifying breast tumor types. Breast cancer, being one of the most common and life-threatening cancers in women, requires accurate diagnostic tools for early detection and effective treatment. The primary objective of this study is to evaluate the accuracy of quantum-assisted models through quantum feature selection methods. Initially, classical machine learning algorithms such as Support Vector Machines (SVM), Decision Trees, Random Forests, and Logistic Regression were applied to the dataset for baseline analysis. Subsequently, a quantum feature map was constructed using the Cirq library, enabling feature transformation based on this map. The classification was performed using the SVM model with the quantum-transformed features. The Logistic Regression and SVM models demonstrated the highest performance among classical machine learning models, achieving an accuracy rate of 96.49%, followed by Random Forest at 94.74% and Decision Tree at 92.11%. In the context of quantum feature transformation, the model utilizing the top five selected features achieved an accuracy rate of 94.74%, in contrast to 98.25% for the model trained with all features. These findings underscore the potential of quantum feature maps in enhancing model performance compared to classical techniques. The results suggest that quantum computing may offer significant advantages when integrated into machine learning frameworks, particularly in domains such as medical diagnostics, where high accuracy is crucial.
This paper presents an empirical comparison of pure quantum, hybrid quantum-classical, and classical support vector machines (SVMs) for binary medical classification on the Breast Cancer Wisconsin dataset. Taking advantage of uniform data preprocessing and feature selection, our hybrid QSVM with quantum kernel mapping coupled with classical optimization achieves accuracy of 98.25% compared with the classical SVM (94.74%) and pure quantum SVM (93.86%). In-depth benchmarking incorporates accuracy, recall, F1-score, and training time, exposing accuracy/computational cost trade-offs. We discuss how dimensionality of features and kernel selection influence model scalability and performance. Albeit constrained to a single dataset and simulation, this work enhances knowledge about hybrid quantum SVM benefits and real-world implications. Future efforts will seek to expand benchmarking to other datasets, include real quantum hardware assessment, and create explanation methods to improve interpretability and clinical usability.