Predictors of urinary tract infection based on artificial neural networks and genetic algorithms
Predictors of urinary tract infection based on artificial neural networks and genetic algorithms
复制标题
DOI：
10.1016/j.ijmedinf.2006.01.005
复制
发表时间：
2007-04-01
影响因子：
4.9
通讯作者：
Gerber, Ben S.
中科院分区：
文献类型：
--
作者：
Heckerling, Paul S.;Canaris, Gay J.;Gerber, Ben S.
背景：在有尿路主诉的女性中，只有50%的人被发现有尿路感染。单独的尿路症状和尿液分析不足以区分有和没有诊断的人。方法：我们使用人工神经网络(ANN)和遗传算法相结合的方法来进化优化的临床变量组合，以预测尿路感染。ANN被应用于212名年龄在19-84岁之间的女性，她们在门诊就诊时有尿路主诉。尿路感染通过不同的模型定义为：尿路病原菌计数=10(5)菌落单位/毫升，尿路病原菌计数=10(2)CFU/毫升。结果：形成了尿路感染和非感染病例的5个变量集，其受试者-操作特征曲线面积从0.853(尿路病原菌计数=10(5)CFU/毫升)到0.792(尿路病原菌计数=10(2)CFU/毫升)。预测变量(包括尿频、排尿困难、尿臭、症状持续时间、糖尿病病史、尿试纸条上的白细胞酯酶、尿液分析中的红细胞、上皮细胞和细菌)根据定义尿路感染的病原体数量而不同。结论：人工神经网络和遗传算法可以准确地预测尿路感染的简约变量集，以及症状、尿检结果和感染之间的新的关系。(C)2006爱思唯尔爱尔兰有限公司。保留所有权利。
Background: Among women who present with urinary complaints, only 50% are found to have urinary tract infection. Individual urinary symptoms and urinalysis are not sufficiently accurate to discriminate those with and without the diagnosis.Methods: We used artificial neural networks (ANN) coupled with genetic algorithms to evolve combinations of clinical variables optimized for predicting urinary tract infection. The ANN were applied to 212 women ages 19-84 who presented to an ambulatory clinic with urinary complaints. Urinary tract infection was defined in separate models as uropathogen counts of >= 10(5) colony-forming units (CFU) per milliliter, and counts of >= 10(2) CFU per milliliter.Results: Five-variable sets were evolved that classified cases of urinary tract infection and non-infection with receiver-operating characteristic (ROC) curve areas that ranged from 0.853 (for uropathogen counts of >= 10(5) CFU per milliliter) to 0.792 (for uropathogen counts of >= 10(2) CFU per milliliter). Predictor variables (which included urinary frequency, dysuria, foul urine odor, symptom duration, history of diabetes, leukocyte esterase on urine dipstick, and red blood cells, epithelial cells, and bacteria on urinalysis) differed depending on the pathogen count that defined urinary tract infection. Network influence analyses showed that some variables predicted urine infection in unexpected ways, and interacted with other variables in making predictions.Conclusions: ANN and genetic algorithms can reveal parsimonious variable sets accurate for predicting urinary tract infection, and novel relationships between symptoms, urinalysis findings, and infection. (c) 2006 Elsevier Ireland Ltd. All rights reserved.