基于神经网络的小细胞肺癌智能辨证研究  

Research on Intelligent Syndrome Differentiation of Small Cell Lung Cancer Based on Neural Network

作　　者：臧晓彤 张培彤[1] ZANG Xiaotong;ZHANG Peitong(Department of Oncology,Guang′anmen Hospital,China Academy of Chinese Medical Sciences,Beijing China 100053)

机构地区：[1]中国中医科学院广安门医院肿瘤科,北京100053

出　　处：《中医学报》2022年第5期1067-1070,共4页Acta Chinese Medicine

摘　　要：目的:基于人工神经网络算法建立小细胞肺癌中医智能辨证模型。方法:采用临床流行病学研究方法,收集小细胞肺癌患者中医四诊信息,依据基于证素理论的分层诊断方法进行中医辨证,采用SPSS23.0软件建立神经网络模型,以受试者工作特征曲线下面积(area under curve,AUC)评估模型优劣。结果:模型训练集总准确率91%,验证集总准确率92.6%,模型平均AUC为0.842。结论:通过人工神经网络算法,可形成准确率较高且符合临床实际的中医智能辨证模型,为小细胞肺癌中医临床诊断提供参考依据。Objective:To establish an intelligent TCM syndrome differentiation model for small cell lung cancer based on artificial neural network algorithm.Methods:The clinical epidemiological research method was used to collect the information of the four diagnosis of TCM in patients with small cell lung cancer,and the TCM syndrome differentiation was carried out according to the hierarchical diagnosis method based on the theory of syndrome elements.The neural network model was established by SPSS23.The area under the curve(AUC)evaluates the merits of the model.Results:The total accuracy of the model training set was 91%,the total accuracy of the validation set was 92.6%,and the average AUC of the model was 0.842.Conclusion:The artificial neural network algorithm can form a TCM intelligent syndrome differentiation model with high accuracy and clinical practice,and provide a reference for TCM clinical diagnosis of small cell lung cancer.

关 键 词：小细胞肺癌 神经网络 智能辨证 证素 

分 类 号：R273.342[医药卫生—中西医结合]