Quantum models predict lung cancer using limited training data in preliminary tests
· Medical Xpressby Florida Atlantic University
edited by Gaby Clark, reviewed by Robert Egan
Gaby Clark
Scientific Editor
Meet our editorial team
Behind our editorial process
Robert Egan
Senior Editor
Meet our editorial team
Behind our editorial process Editors' notes
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
fact-checked
trusted source
proofread
The GIST Add to Preferred Sources
Developing reliable machine learning models for health care can be challenging when only small datasets are available. This challenge motivates research into whether quantum computing approaches can learn useful patterns from limited symptom and risk-factor data.
A research team, led by Arslan Munir, Ph.D., professor in Florida Atlantic University's Department of Electrical Engineering and Computer Science within the College of Engineering and Computer Science, and director of the Intelligent Systems, Computer Architecture, Analytics, and Security Laboratory, evaluated quantum machine learning approaches in simulation and on quantum hardware using symptom and risk-factor data for lung cancer prediction under limited training data.
The study, published in Discover Quantum Science, "Inferring lung cancer under limited learning data through gate-based and annealing-based quantum techniques," provides a common framework for evaluating different quantum machine learning methods under the same data preparation and testing conditions.
"Our goal was to examine how different quantum learning approaches perform when the amount of training data is deliberately constrained," said Munir. "By evaluating multiple methods within a common experimental framework, we can better understand their capabilities and limitations and identify directions that warrant further investigation."
Testing quantum methods with limited data
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. To balance the cancer and noncancer categories, they used a statistical technique that generates synthetic examples, producing an experimental dataset of 540 samples. These additional samples did not represent newly recruited patients.
An optimization-based feature-selection method narrowed the input variables to 10. The researchers then evaluated three classification methods: quantum support vector machines, quantum k-nearest neighbors and quantum boosting. In each of five evaluation rounds, the models were trained on 108 samples and tested on the remaining 432.
The study examined two major approaches to quantum computing: quantum annealing and gate-based computing. The team evaluated implementations across Qiskit, Cirq, PennyLane, OpenJij and D-Wave, enabling comparisons across several software frameworks and computational approaches.
Annealing leads the main evaluation
D-Wave's annealing quantum computers used in a quantum support vector machine framework achieved the highest reported accuracy in the main evaluation, reaching 94.31% in simulation and 91.90% on quantum hardware. Testing on hardware allowed the researchers to examine how the method performed beyond a simulated environment.
"FAU's research highlights how D-Wave's annealing quantum computers can be used to advance AI and machine learning," said Catherine Potts, Ph.D., manager of technical account management at D-Wave Quantum Inc. "By applying our technology to a challenging health care use case, the researchers demonstrate its potential to extract valuable insights in data-constrained environments, opening new possibilities for quantum-powered AI across health care and other data-intensive industries."
The study's contribution extends beyond its highest accuracy score. By applying a common evaluation framework, the researchers examined how the choice of classification method, selected variables and computing platform affected performance. The findings offer a basis for further research into quantum machine learning for structured health care data.
"This study reflects Florida Atlantic's efforts to connect quantum computing research with meaningful application questions," said Stella Batalama, Ph.D., dean of FAU's College of Engineering and Computer Science. "Careful comparisons and testing on quantum hardware help build the evidence needed to assess where these technologies may be useful and what challenges remain."
Clinical validation remains ahead
The researchers emphasize that the findings are preliminary. The dataset contains symptoms and risk factors rather than medical images, pathology findings, laboratory results or cancer-stage information. The reported accuracy reflects the study's augmented dataset and evaluation procedure.
Future research will examine larger datasets from multiple institutions and explore combining symptom information with imaging or genomic data. The team also plans to investigate methods that make model predictions easier to interpret.
"These results provide a starting point for further evaluation," said Munir. "The next step is to determine how well these approaches generalize to independent clinical datasets and whether they can offer useful support within carefully validated health care workflows."
More information
Muhammad Minoar Hossain et al., Inferring lung cancer under limited learning data through gate-based and annealing-based quantum techniques, Discover Quantum Science (2026). DOI: 10.1007/s44464-026-00038-4
Key medical concepts
Clinical categories
Pulmonary medicineOncology Provided by Florida Atlantic University Who's behind this story?
Gaby Clark
MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile →
Robert Egan
Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →
Citation: Quantum models predict lung cancer using limited training data in preliminary tests (2026, November 2) retrieved 2 November 2026 from https://medicalxpress.com/news/2026-11-quantum-lung-cancer-limited-preliminary.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.