%0 Journal Article
%T 基于机器学习算法的乳腺癌诊断分析<br>Analysis of Breast Cancer Diagnosis Based on Machine Learning Classifier Algorithm
%A 张力芝
%J Operations Research and Fuzziology
%P 397-405
%@ 2163-1530
%D 2024
%I Hans Publishing
%R 10.12677/orf.2024.144409
%X 机器学习作为人工智能的重要支撑技术&#65292;在多个领域都得到了极为广泛的应用&#65292;如图像识别、自然语言处理、医学诊断等。本文针对威斯康星医院乳腺癌数据&#65292;采用机器学习中的k近邻、朴素贝叶斯、决策树以及神经网络这四类分类器算法进行分析诊断&#65292;即通过收集和预处理乳腺癌数据集&#65292;采用机器学习分类方法得到对应的混淆矩阵&#65292;计算各分类器的性能评价指标&#65292;并用10折交叉验证结果的可靠性&#65292;分析最适合的机器学习诊断方法。实验结果表明&#65306;k近邻法的评价指标值最高&#65292;误判率最低&#65292;相比之下更适合该乳腺癌的诊断。<br>Machine learning, as a crucial underpinning technology for artificial intelligence, has found extensive applications in various domains such as image recognition, natural language processing, and medical diagnosis. This study focuses on the analysis and diagnosis of breast cancer using four classification algorithms from machine learning: k-nearest neighbors, naive Bayes, decision trees, and neural networks. Specifically, this paper utilizes these algorithms for data collection and preprocessing of the Wisconsin Hospital Breast Cancer Data Set. Subsequently, employing machine learning classification methods to generate corresponding confusion matrices and calculate performance evaluation metrics for each classifier; furthermore, assessing the reliability of the results through 10-fold cross-validation to identify the most suitable machine learning diagnostic approach. The experimental findings indicate that k-nearest neighbors exhibit the highest evaluation index values and lowest misjudgment rates compared to other classifiers, making it more suitable for breast cancer diagnosis.
%K 乳腺癌&#65292
%K k近邻&#65292
%K 朴素贝叶斯&#65292
%K 决策树&#65292
%K 神经网络<br>Breast Cancer
%K k-Nearest Neighbor
%K Naive Bayesian
%K Decision Tree
%K Neural Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=94123