基于人工智能的中医证候分类算法研究  

Research on TCM Syndrome Classification Algorithm Based on Artificial Intelligence

作　　者：杜昉臻 何圆姣 冯西贝 刘国华[1] Du Fangzhen;He Yuanjiao;Feng Xibei;Liu Guohua(Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology,College of Electronic Information Technology and Optical Engineering,Nankai University,Tianjin 300350,China)

机构地区：[1]南开大学电子信息与光学工程学院,天津市光电传感器与传感网络技术重点实验室,天津300350

出　　处：《南开大学学报（自然科学版）》2023年第2期12-16,共5页Acta Scientiarum Naturalium Universitatis Nankaiensis

基　　金：中央高校基本科研业务费专项资金。

摘　　要：基于中医脏腑辩证的28种常见临床证候分类,探讨了多标签K近邻、全连接神经网络、一维卷积神经网络3种算法原理,测试、分析、比较了3种算法的优劣.其中,全连接神经网络模型的分类算法具有较高的准确率,可达84.48%.28 common clinical syndromes is classified based on the dialectics of TCM viscera, explores three algorithm principles of multi-label K-nearest neighbor, fully connected neural network, and one-dimensional convolutional neural network with testing, analyzing and comparing the advantages and disadvantages of the three algorithms. Among these algorithms, the classification algorithm of the fully connected neural network model has a high accuracy rate of up to 84.48%. The use of neural network model algorithm not only improves the accuracy of TCM diagnosis, but also more comprehensively diagnosed diseases, and has a good application prospect in TCM clinical diagnosis.

关 键 词：中医脏腑辨证 人工智能 神经网络 中医证候分类 

分 类 号：R241.6[医药卫生—中医诊断学]