Arslan Munir, Ph. D., of Florida Atlantic University led a study demonstrating 94.31% accuracy in simulation using D-Wave’s annealing quantum computers and a quantum support vector machine framework for lung cancer prediction. The researchers began with a publicly available dataset containing 309 records with information such as smoking history, coughing, wheezing, fatigue and chest pain, along with a lung cancer label. Munir said the study established a common framework for evaluating different quantum machine learning methods under the same data preparation and testing conditions.
Quantum Support Vector Machines Predict Lung Cancer with High Accuracy
D-Wave’s annealing quantum computers achieved 94% accuracy. Researchers at Florida Atlantic University specifically evaluated this approach using a dataset of 309 patient records to assess its ability to discern patterns from limited information, a common challenge in medical diagnostics. Arslan Munir, Ph. D., led the study, focusing on a dataset of 309 patient records detailing symptoms and risk factors; the team augmented this with synthetically generated data to create a 540-sample experimental set.
The researchers employed an optimization-based feature selection method, narrowing the initial variable set to 10 inputs before evaluating quantum support vector machines, k-nearest neighbors, and boosting algorithms. Each model underwent five rounds of training on 108 samples and testing on the remaining 432, allowing for robust performance assessment.
The investigation extended beyond simulation, with the team testing implementations across multiple software frameworks, OpenJij and D-Wave, and evaluating both quantum annealing and gate-based computing approaches. Achieving 91.90% accuracy on actual quantum hardware allowed the researchers to examine how the method performed beyond a simulated environment.
Catherine Potts, Ph.D. said, “By applying our technology to a challenging healthcare use case, the researchers demonstrate its potential to extract valuable insights in data-constrained environments, opening new possibilities for quantum-powered AI across healthcare and other data-intensive industries.” Further research will focus on validating these findings with independent clinical datasets, as the findings offer a basis for further research into quantum machine learning for structured healthcare data. Munir also emphasized the importance of standardized evaluation, stating, “By evaluating multiple methods within a common experimental framework, we can better understand their capabilities and limitations and identify directions that warrant further investigation.”
This study reflects Florida Atlantic’s efforts to connect quantum computing research with meaningful application questions.
Stella Batalama, Ph
Comparative Evaluation of Quantum Computing Frameworks for Limited Healthcare Data
This hardware validation is important because it moves beyond purely simulated environments and begins to assess real-world viability for clinical applications. The study, titled “Inferring lung cancer under limited learning data through gate-based and annealing-based quantum techniques,” established a standardized methodology for evaluating quantum machine learning methods, enabling researchers to isolate the impact of classification techniques, variable selection and the underlying computing platform.
Stella Batalama, Ph. D., dean of FAU’s College of Engineering and Computer Science, emphasized the importance of this comparative approach, stating, “Careful comparisons and testing on quantum hardware help build the evidence needed to assess where these technologies may be useful and what challenges remain.” This focus on a “common framework” means the findings extend beyond lung cancer prediction, offering a template for assessing quantum machine learning across diverse healthcare datasets.
Despite the promising results, the researchers caution that these findings represent an initial step, and further validation is necessary. The team acknowledges the need to assess how well these models generalize to independent clinical datasets, noting that successful implementation requires careful integration into existing healthcare workflows. Florida Atlantic University continues to invest in quantum research, aiming to position itself as a leading institution in the emerging quantum economy through the FAU Center for Quantum Technologies.
Our goal was to examine how different quantum learning approaches perform when the amount of training data is deliberately constrained.
Arslan Munir, Ph
See today’s quantum computing news on Quantum Zeitgeist for the latest breakthroughs in qubits, hardware, algorithms, and industry deals.
