TD SYNNEX Newsflash

How quantum computing could predict early lung cancer

Artificial Intelligence Trending News
By TD SYNNEX Newsflash 16th November 2026

Researchers at Florida Atlantic University (FAU) have demonstrated how quantum computing could support machine learning models used to predict lung cancer, with accuracy reaching 94.31% in simulations and 91.90% on a physical quantum computer.

The research explores a wider challenge facing artificial intelligence (AI) and machine learning: developing reliable models when only limited training data is available. By combining quantum computing with machine learning, the researchers investigated whether these technologies could identify patterns in symptoms and risk factors associated with lung cancer.

How quantum computing could predict early lung cancer

While the findings are preliminary, they demonstrate the potential for quantum computing to complement conventional AI and machine learning when working with limited datasets.

How quantum machine learning was used to predict lung cancer

Published in Discover Quantum Science, the FAU study evaluated quantum machine learning approaches in both simulated environments and on physical quantum computers.

The researchers compared three classification methods: quantum support vector machines, quantum k-nearest neighbours and quantum boosting. They tested these across five computing frameworks, including Qiskit, Cirq, PennyLane, OpenJij and D-Wave.

The research began with 309 records containing symptoms and risk factors including smoking, coughing, wheezing, fatigue and chest pain. To balance the cancer and non-cancer categories, researchers generated synthetic examples, creating an experimental dataset of 540 samples. These additional samples did not represent new patients.

The researchers then narrowed the input variables to 10 to assess how effectively different quantum computing approaches could identify patterns in the data.

D-Wave quantum computers achieved the highest accuracy

A quantum support vector machine using D-Wave technology produced the study's highest reported accuracy, reaching 94.31% in simulation and 91.90% on a physical quantum computer.

The researchers said that comparing different approaches under the same conditions could provide a benchmark for understanding the capabilities and limitations of quantum machine learning methods.

The findings also show how quantum machine learning can move beyond simulated environments, supporting further investigation into its potential practical applications.

Why further research is needed

The results do not mean quantum computers can currently diagnose lung cancer in clinical settings.

FAU said the research is preliminary and does not represent a clinically validated diagnostic tool. The dataset did not include medical imaging, pathology results, laboratory findings or information about cancer stage. The additional samples were also generated statistically rather than representing new patients. Independent clinical datasets and further validation would therefore be needed before these techniques could support real-world healthcare decisions.

Beyond healthcare, the study highlights a broader potential role for quantum computing in supporting AI and machine learning where high-quality training data is limited. As quantum technologies develop, research such as this could help identify where they may offer practical advantages alongside conventional computing.

Today’s news was brought to you by TD SYNNEX – the UK’s number one solutions distributor.