Quantum models predict lung cancer using limited training data in preliminary tests
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 from Florida Atlantic University evaluated quantum machine learning approaches for predicting lung cancer using limited training data. The study, published in Discover Quantum Science, aimed to assess how various quantum learning methods perform with constrained data. They used a dataset of 309 records, balanced by generating synthetic examples, resulting in 540 samples.
Feature selection reduced the input variables to 10. Three classification methods were evaluated: quantum support vector machines, quantum k-nearest neighbors, and quantum boosting. Three quantum computing approaches were tested: gate-based computing and two quantum annealing methods. D-Wave's annealing quantum computer achieved the highest accuracy in simulation (94.31%) and on hardware (91.90%).
The study highlights the potential of D-Wave's annealing quantum computers to advance AI and machine learning in data-constrained environments. However, the findings are preliminary, and future research will explore larger datasets and combine symptom information with imaging or genomic data.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
