摘要
目的 探讨人工神经网络 (ANN )用于疾病分类研究的前景。方法 利用某矿区 1996年糖尿病现况调查资料 ,采用学习向量量化 (LVQ )网络和判别分析方法进行糖尿病 /糖耐量 (DM IGT)异常 正常状态的判别比较 ;同时人为设置变量缺损值 ,检验LVQ网络对缺失数据的适应性。结果 LVQ网络结构为 2 5→ 13→ 3 ;网络判断准确率为 96.98% ,对血糖异常者的正确判断率为92 .45%。利用逐步判别分析建立的含 11个变量的判别方程的判断准确率为 87.3 4 % ,对血糖异常者的正确判断率为 85.53 %。LVQ网络对带缺失项样本的误判比例为 1 3 0 ,判别分析则为 7 3 0。结论 利用LVQ网络进行疾病分类预测 ,不仅能获得更好的预测效果 ,而且对资料的类型、分布不作任何限制 ,也不需要对分析变量做任何处理 ,还能很好地处理带缺失项的资料 。
ObjectiveTo discuss the potential applic at ion of artificial neural network (ANN) on the epidemiological classification of disease. MethodsLearning vector quantization neural network (LVQN N) and discriminate analysis were applied to data from epidemiological survey in a mine in 1996. ResultsThe structure of LVQNN was 25→13→3. The total veracity rates was 96.98 %, and 92.45 % among the abnormal blood glucose individuals. Through stepwise discriminate analysis, the discriminate equations were established including 11 variables with a total veracity rate of 87.34 %, but was 85.53 % in the abnormal blood glucose individuals. Further anal ysis on 30 cases with missing values showed that the disagreement ratio of LVQ w as 1/30, lower than that of discriminate analysis of 7/30. ConclusionsCompared to the conventional statistics m ethod, LVQ not only showed better prediction precision, but could treat data wi th missing values satisfactorily plus it had no limit to the type or distributi on of relevant data, thus provided a new powerful method to epidemiologic predi ction.
出处
《中华流行病学杂志》
CAS
CSCD
北大核心
2003年第11期1052-1056,共5页
Chinese Journal of Epidemiology
关键词
人工神经网络
糖尿病
糖耐量异常
疾病分类
调查
Artificial neural network
Learning vector quantization neural network
Diabetes mellitus/insulin glucose tolerance
Classi fication of disease
