Quantum Machine Learning and Data Re-Uploading: Evaluation on Benchmark and Laboratory Medicine Data Sets
Thomas J S Durant, Seung Joo (Erin) Lee, Sarah Nixon Dudgeon, Elizabeth Knight, Brent G. Nelson, H. Patrick Young, Lucila Ohno-machado A, Wade L. Schulz
ABSTRACT Background Quantum machine learning is an emerging field that may offer unique advantages over classical machine learning but has not been extensively studied with real-world healthcare data of practical size. This study evaluates the performance of a recently proposed quantum machine learning algorithm—quantum circuits with data re-uploading—compared to classical machine learning and other common quantum algorithms, using both benchmarking data and real-world laboratory medicine data. Methods Four datasets containing between 2 and 30 features were selected for evaluation. The quantum re-uploading algorithm was compared against variational quantum classifiers, quantum neural networks and four, commonly used classical machine learning algorithms. Initial, baseline comparisons of classification performance (F1 score) were conducted using all algorithms across the four datasets. Configuration parameters were then optimized for the quantum data re-uploading algorithm using a previously published dataset of plasma amino acid profiles to determine the impact of optimization on classification performance, followed by a final comparison against classical ML algorithms. Results Baseline comparisons of quantum re-uploading showed superior classification performance on lower-dimensional datasets compared to quantum and linear ML algorithms. However, performance declined significantly as the number of input features increased. While optimization improved classification performance, marked variability was observed. Following optimization, the quantum re- uploading algorithm again performed comparably to linear algorithms but had lower classification performance on the plasma amino acid dataset compared to non-linear classical algorithms. Conclusion This study suggests that quantum data-reuploading algorithms can achieve classification performance comparable to some classical methods on lower-dimensional datasets, presenting opportunities for early research applications in laboratory medicine. However, while optimizing configuration parameters can improve classification performance, further advancements in quantum hardware and algorithm design will likely be necessary for quantum machine learning to become practically viable in laboratory medicine, and biomedical research more broadly.
ABSTRACT Background Quantum machine learning is an emerging field that may offer unique advantages over classical machine learning but has not been extensively studied with real-world healthcare data of practical size. This study evaluates the performance of a recently proposed quantum machine learning algorithm—quantum circuits with data re-uploading—compared to classical machine learning and other common quantum algorithms, using both benchmarking data and real-world laboratory medicine data. Methods Four datasets containing between 2 and 30 features were selected for evaluation. The quantum re-uploading algorithm was compared against variational quantum classifiers, quantum neural networks and four, commonly used classical machine learning algorithms. Initial, baseline comparisons of classification performance (F1 score) were conducted using all algorithms across the four datasets. Configuration parameters were then optimized for the quantum data re-uploading algorithm using a previously published dataset of plasma amino acid profiles to determine the impact of optimization on classification performance, followed by a final comparison against classical ML algorithms. Results Baseline comparisons of quantum re-uploading showed superior classification performance on lower-dimensional datasets compared to quantum and linear ML algorithms. However, performance declined significantly as the number of input features increased. While optimization improved classification performance, marked variability was observed. Following optimization, the quantum re- uploading algorithm again performed comparably to linear algorithms but had lower classification performance on the plasma amino acid dataset compared to non-linear classical algorithms. Conclusion This study suggests that quantum data-reuploading algorithms can achieve classification performance comparable to some classical methods on lower-dimensional datasets, presenting opportunities for early research applications in laboratory medicine. However, while optimizing configuration parameters can improve classification performance, further advancements in quantum hardware and algorithm design will likely be necessary for quantum machine learning to become practically viable in laboratory medicine, and biomedical research more broadly.
Quantum machine learning integrates quantum computing with classical machine learning techniques to enhance computational power and efficiency. A major challenge in quantum machine learning is developing robust quantum classifiers capable of accurately processing and classifying complex datasets. In this work, we present an advanced approach leveraging data re-uploading, a strategy that cyclically encodes classical data into quantum states to improve classifier performance. We examine two cost functions, fidelity and trace distance, across various quantum classifier configurations, including single-qubit, two-qubit, and entangled two-qubit systems. Additionally, we evaluate four optimization techniques (L-BFGS-B, COBYLA, Nelder-Mead, and SLSQP) to determine their effectiveness in optimizing quantum circuits for both linear and non-linear classification tasks. Our results show that the choice of optimization method significantly impacts classifier performance, with L-BFGS-B and COBYLA often yielding superior accuracy. The two-qubit entangled classifier shows improved accuracy over its non-entangled counterpart, albeit with increased computational cost. Also, the two-qubit entangled classifier is the best option for real-world random datasets in terms of accuracy and computational cost. Linear classification tasks generally exhibit more stable performance across optimization techniques compared to non-linear tasks. Our findings highlight the potential of data re-uploading in quantum machine learning, outperforming existing quantum classifier models in terms of accuracy and robustness. This work contributes to the growing field of quantum machine learning by providing a comprehensive comparison of classification strategies and optimization techniques in quantum computing environments, offering a foundation for developing more efficient and accurate quantum classifiers.
Abstract Quantum machine learning integrates quantum computing with classical machine learning techniques to enhance computational power and efficiency. A major challenge in Quantum machine learning is developing robust quantum classifiers capable of accurately processing and classifying complex datasets. In this work, we present an advanced approach leveraging data re-uploading, a strategy that cyclically encodes classical data into quantum states to improve classifier performance. We examine two cost functions—fidelity and trace distance—across various quantum classifier configurations, including single-qubit, two-qubit, and entangled two-qubit systems. Additionally, we evaluate four optimization techniques (L-BFGS-B, COBYLA, Nelder-Mead, and SLSQP) to determine their effectiveness in optimizing quantum circuits for both linear and non-linear classification tasks. Our results show that the choice of optimization method significantly impacts classifier performance, with L-BFGS-B and COBYLA often yielding superior accuracy. The two-qubit entangled classifier shows improved accuracy over its non-entangled counterpart, albeit with increased computational cost. Also, the two-qubit entangled classifier are the best option for real word random dataset in order to accuracy and computational cost. Linear classification tasks generally exhibit more stable performance across optimization techniques compared to non-linear tasks. Our findings highlight the potential of data re-uploading in Quantum machine learning outperforming existing quantum classifier models in terms of accuracy and robustness. This work contributes to the growing field of Quantum machine learning by providing a comprehensive comparison of classification strategies and optimization techniques in quantum computing environments, offering a foundation for developing more efficient and accurate quantum classifiers.
Quantum machine learning (QML) is a new field in its infancy, promising performance enhancements over many classical machine learning (ML) algorithms. Data reuploading is a QML algorithm with a focus on utilizing the power of a singular qubit as an individually capable classifier. Recently, there have been studies set out to explore the concept of data re-uploading in a classification setting, however, important aspects are often not considered in experiments, which may hinder our understanding of the methodology’s performance. In this work, we conduct an analysis of the single-qubit data re-uploading methodology, in relation to the effect that system depth has on classification and robustness performances against the influence of environmental noise during training. This is aimed towards bridging together previous works in order to solidify the concepts of the methodology, and provide reasonable insight into how transferable the methodology is when applied to non-synthetic data. To further demonstrate the findings, we also analyse the results of a case study using a subset of MNIST data. From this work, our experimental results support that an increase in system depth can lead to higher classification performances, as well as improved stability during training in noisy environments, with the sharpest performance improvements seemingly occurring between 1–3 uploading layer repetitions. Leading on from our experimental results, we suggest areas for further exploration, to ensure we can maximize classification performance when using the data re-uploading methodology.
Background Artificial Intelligence (AI) incorporation within healthcare applications has significantly helped in the improvement of healthcare diagnostics, patient forecasting, and clinical decision-making. The steady growing of medical data in terms of quantity, quality, and dimension poses more significant problems for traditional AI methods in terms of size, time, and computational efficiency. However, classical machine learning models often struggle with high-dimensional, imbalanced, and heterogeneous medical datasets, which limits their scalability and generalizability. The Quantum Artificial Intelligence (QAI) model, which combines quantum computing and machine learning in a complementary way, has emerged as one of the main trends to defeat these problems. This complementary approach is gaining more popularity, with the most advanced work being developed in this area, as it offers a fundamental explanation of current complexities and the underlying principles and their applications. Methodology This paper begins with the basic concepts of quantum computing and where it overlaps with AI. It then moves to a comparative approach, discussing various quantum machine learning algorithms such as quantum support vector machines, quantum neural networks, and variational quantum circuits. A comparative evaluation of quantum support vector machine, variational quantum classifier, quantum neural network, quantum K-means, and quantum Boltzmann machine is conducted using the Pima Indians Diabetes dataset to assess model behaviour and performance under standard metrics. Further detail is provided on the theoretical and practical implications of QAI in medical imaging, genomics, electronic health records, and drug discovery. Additionally, this paper examines platforms, tools, and quantum hardware used for QAI research, and discusses unique challenges currently faced in quantum technology. Results Unlike prior surveys that primarily provide conceptual overviews, this paper uniquely combines a comprehensive review with practical benchmarking of multiple quantum machine learning models on a benchmark medical dataset. This provides comparative insights into algorithmic performance under real-world constraints, particularly in relation to high-dimensional medical data, genomic data, electronic health records with large number of clinical attributes, radiology images, etc. In this study, dimensionality arises from multivariate clinical features encoded into quantum feature maps and the limitations of current quantum systems. Conclusion This paper aims to serve as a starting point for researchers and practitioners interested in the potential of quantum-enhanced AI to transform health data analytics. By identifying current limitations, evaluating the performance of emerging quantum machine learning approaches, and outlining gaps in the literature, the paper highlights future research directions necessary to advance QAI in healthcare. Overall, the findings outline both the potential and practical constraints of quantum models, offering a foundation for future work toward scalable, clinically applicable QAI solutions.
Quantum Machine Learning (QML) has emerged as an interdisciplinary field that harnesses the potential of quantum computing to revolutionize classical machine learning paradigms. This paper presents a benchmarking study focused on four quantum classifier algorithms: Quantum Support Vector Classifier (QSVC), Variational Quantum Circuit (VQC), Quantum Neural Network Classifier (QNNC) and Pegasos Quantum Support Vector Classifier (PegasosQSVC). These quantum classifiers hold promise for unlocking quantum advantages in classification tasks. However, a systematic assessment of their performance across diverse datasets is yet to be fully explored. In this research study, we evaluate and compare the classification performance of quantum machine learning classifiers on various datasets (Breast Cancer, Diabetes, and Titanic) and compare them to a classical model. Our findings revealed that PegasosQSVC consistently maintained high performance across all datasets with the highest average accuracy, recall, and F1-score values of 0.81, 0.72, and 0.71, respectively, followed by VQC, followed by VQC, while QSVC and QNNC perform variably. Nevertheless, QSVC was found to balance performance and training time, achieving an average accuracy of 0.81 and a training time of 177 seconds. Overall, the classical model surpassed QML models as it was up to 10% higher in average accuracy.
Abstract This paper presents, via an explicit example with a real-world dataset, a hands-on introduction to the field of quantum machine learning (QML). We focus on the case of learning with a single qubit, using data re-uploading techniques. After a discussion of the relevant background in quantum computing and machine learning we provide a thorough explanation of the data re-uploading models that we consider, and implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK. We find that, as in the case of classical neural networks, the number of layers is a determining factor in the final accuracy of the models. Moreover, and interestingly, the results show that single-qubit classifiers can achieve a performance that is on-par with classical counterparts under the same set of training conditions. While this cannot be understood as a proof of the advantage of quantum machine learning, it points to a promising research direction, and raises a series of questions that we outline.