基于随机森林的中医电子病历数据分类系统设计  

Design of Chinese Medical Electronic Medical Records Data Classification System of Based on Random Forest

作　　者：吕侃 陶奕 顾捷飞 钟臻[1] LV Kan;TAO Yi;GU Jie-fei;ZHONG Zhen(Shanghai Municipal Hospital of Traditional Chinese Medicine,Shanghai 200071 China)

机构地区：[1]上海中医药大学附属市中医医院,上海200071

出　　处：《自动化技术与应用》2024年第8期133-135,共3页Techniques of Automation and Applications

摘　　要：应用当前系统进行电子病历数据分类时,分类精度低,效率也低。为此设计基于随机森林的中医电子病历数据分类系统。以S3C2440A和PGL22G分别为核心设计运行控制和通信控制模块实现硬件部分对软件功能的支撑。结合中医电子病历数据特点,选择数据分类特征。由CART算法生成随机森林基础分类器,利用训练数据集对其训练,确定分类参数完成分类系统设计。通过实验测试,该系统的分类精度高于92%,且分类效果优于两对比系统,运行性能优越。When using the current system to classify EMR data,the classification accuracy and efficiency are low.In order to improve the above defects,an automatic classification system of TCM electronic medical record data based on random forest is designed.Taking S3C2440A and PGL22G as the core,the operation control and communication control modules are designed to realize the support of hardware to software functions.Combined with the characteristics of TCM electronic medical record data,the data classification characteristics are selected.The cart algorithm generates the random forest basic classifier,trains it with the training data set,determines the classification parameters,and completes the design of the classification system.Through the experimental test,the classification accuracy of the system is higher than 92%,and the classification effect is better than the two comparison systems.

关 键 词：随机森林 中医电子病历 数据自动分类 信息熵 系统设计 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论]