Breast cancer prediction based hybrid comparison of multiple classification algorithms
LI Li
WANG Yong
LU Ning
LIN Kuo-yi
Abstract：Breast cancer is an important cause of the death of female cancer patients due to its easy recurrence and high mortality. Early diagnosis of breast cancer increases the probability of curing cancer. Therefore, it is particularly important to improve the accuracy of early diagnosis. The traditional early diagnosis mainly relies on human experience to judge breast cancer by analyzing clinical or examination data, and sufficient accuracy cannot be guaranteed. Many researchers have proposed various machine learning methods to improve prediction accuracy and efficiency. However, the current algorithms have high computational complexity, and it is difficult to directly determine the appropriate algorithm from a variety of algorithms. This paper experiments with ten popular classification algorithms, compares the differences between the algorithms, and applies quantum support vector machines to speed up the computation process. Numerical experiments show that support vector machines and artificial neural network achieve the best prediction results, verifying the effectiveness of hybrid comparison of multiple classification algorithms.
Keywords：breast cancersupport vector machinesclassificationquantum computing
Publication Date：2021-10-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 1503-1510 )