基于机器学习的前列腺肿瘤患者分类预测研究  

Research on Classification Prediction for Prostate Neoplasm Patients Based on Machine Learning

作　　者：李佳林 侯利明 黄俊[3] LI Jialin;HOU Liming;HUANG Jun(Sichuan Vocational College of Health and Rehabilitation,Zigong 643000,China;Xinxiang Medical University,Xinxiang 453003,China;Zigong First People's Hospital,Zigong 643000,China)

机构地区：[1]四川卫生康复职业学院,四川自贡643000 [2]新乡医学院,河南新乡453003 [3]自贡市第一人民医院,四川自贡643000

出　　处：《现代信息科技》2024年第17期73-77,共5页Modern Information Technology

基　　金：自贡市哲学社会科学重点研究基地运动与健康创新研究中心(YDJKY23-08)。

摘　　要：针对临床中不能实时高效筛查前列腺患者并进行分类的难题,构建了基于BP神经网络、随机森林(RF)算法、径向基函数(RBF)和卷积神经网络(CNN)的4种机器学习模型,以快速鉴别不同类型的前列腺患者。利用参数和交叉验证不断优化模型,同时采用准确率、精确率、召回率和两者的调和平均值4个指标来评价模型性能。结果发现,BP神经网络、RF算法、RBF和CNN的准确率分别为0.930、0.965、0.877、0.982,说明4种方法都能较好地完成对前列腺患者的分类预测,其中CNN分类预测效果最好,可以为前列腺癌的早期临床筛查提供参考。In view of the clinical difficulties of not being able to screen prostate patients efficiently and carry out classification in real time,four Machine Learning models based on BP Neural Network,Random Forest(RF)Algorithm,Radial Basis Function(RBF),and Convolutional Neural Network(CNN)are constructed to identify different types of prostate patients quickly.The models are continuously optimized using parameters and Cross-Validation,and the performance of the models is evaluated using four indicators of accuracy,precision,recall,and the harmonic mean of the two.The accuracy of the BP Neural Network,RF Algorithm,RBF and CNN is 0.930,0.965,0.877 and 0.982,respectively,indicating that the four methods can all perform classification prediction of prostate patients well.Among them,CNN has the best classification prediction effect and can provide a reference for the early clinical screening of prostate cancer.

关 键 词：前列腺增生 前列腺腺癌 机器学习 分类预测 混淆矩阵 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]