基于知识的模糊神经网络临床路径变异分析方法  

Analyzing Method for Clinical Pathway Variations Based on Fuzzy Neural Network with Knowledge

作　　者：杜刚[1] 江志斌[1] 刁晓娣[2] 姚阳[3] 

机构地区：[1]上海交通大学工业工程与物流工程系,上海200240 [2]上海市普陀区中心医院,上海200062 [3]上海市第六人民医院,上海200233

出　　处：《上海交通大学学报》2010年第11期1600-1604,共5页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目(60774103);上海交通大学重大项目培育基金项目

摘　　要：探索了基于Mamdani、Takagi-Sugeno模型的模糊神经网络,以及BP神经网络在临床路径控制中的应用.提出了基于知识的模糊神经网络临床路径变异分析方法,以骨肉瘤化疗临床路径肝中毒变异为例进行了实例验证.分析了几种方法的有效性以及各自的优缺点.结果表明,在处理临床路径变异方面,基于知识的模糊神经网络与标准的BP神经网络相比,具有明显的优越性.The application of the Mamdani,Takagi-Sugeno fuzzy neural network,and BP neural network in clinical pathway control was investigated.The analyzing method for clinical pathway variations based on fuzzy neural network with knowledge was given.Finally,a case study on liver poisoning of osteosarcoma preoperative chemotherapy was used to validate the proposed method,and their effectiveness,and respective advantages and disadvantages were analyzed.The result shows that knowledge fuzzy neural networks have obvious advantages over standard neural networks for analyzing and reasoning of clinical pathway variations.

关 键 词：知识模糊神经网络 临床路径 变异 肝中毒 

分 类 号：R197.323[医药卫生—卫生事业管理]