Quantum Models Tested for Lung Cancer Prediction
Florida Atlantic University researchers evaluated quantum machine learning methods on a small symptom dataset to assess early lung cancer prediction.
Updated on Nov. 2, 2026 in Quantum Computing
Live Poll
Would you trust an AI tool to help doctors screen you for lung cancer?
Researchers at Florida Atlantic University tested quantum machine learning approaches for predicting lung cancer under limited training data. The study used a public dataset of 309 records containing symptoms and risk factors, and was published in Discover Quantum Science.
Why it matters
Developing reliable machine learning models for healthcare is challenging when only small datasets are available. The work explores whether quantum methods can contribute to prediction tasks in that constrained setting, which is relevant to research centers in Boca Raton and across Florida.
The study evaluated quantum support vector machines, quantum k-nearest neighbors, and quantum boosting across Qiskit, Cirq, PennyLane, OpenJij, and D-Wave, with 10 input variables after feature selection. The dataset of 309 records was expanded to 540 samples through synthetic balancing, and the researchers have not yet tested larger multi-institution data.
The players
Florida Atlantic University
A public research university based in Boca Raton, Florida, which conducted the study through its research team.
D-Wave
A quantum computing company whose annealing quantum computers were used to run the quantum support vector machine experiments.
The details
The team applied a common experimental framework to compare multiple quantum learning methods under identical data preparation and testing conditions. The dataset included smoking history, coughing, wheezing, fatigue, and chest pain, and the researchers plan to examine larger datasets and explore combining symptom data with imaging or genomic information.
Timeline
November 2, 2026: Florida Atlantic University published its news release on the lung cancer quantum study.
The Tech Race
The study extends the use of D-Wave annealing quantum computers, which reached 91.90% accuracy on hardware in this framework, into medical prediction tasks. It positions annealing-based approaches alongside gate-model platforms such as Qiskit, Cirq, and PennyLane, which were evaluated in the same experiments.
The findings are early and based on a symptom-only dataset, so they do not yet change how lung cancer is screened or diagnosed. Patients and clinicians should continue to rely on established screening and diagnostic methods while the approach is tested on larger and more varied data.
The takeaway
Quantum machine learning is being tested on medical prediction problems where data is scarce, a setting that challenges conventional methods. Results on symptom data are a starting point, and broader validation on richer medical data will determine whether the approach is useful.
Further reading
For more on how quantum hardware is being applied beyond the lab, see Quantum Computing coverage.
More information
Read the full peer-reviewed study in Discover Quantum Science for methods and results.
Live Poll
Would you trust an AI tool to help doctors screen you for lung cancer?
