神经网络模型建立及在医院感染病例预警中应用
|
摘要
目的为解决医院感染病例"上报难"问题,初步建立神经网络模型在医院感染病例预警中的应用。方法通过神经网络与决策树分类器相结合,2017年3月1—31日通过对某三甲医院特定时间内抽取的4 911例感染病例的信息进行分析,得到一个由训练过后神经网络生成的规则算法,再由该方法对另一个时段内患者信息进行预测,并将预测结果与实际结果进行对比,以寻求一种针对医院感染信息系统最佳的数据分析核心算法。结果在模型的拟合程度上,classification tree模型优于neural network模型,同时2者大大优于logistics模型;在预测结果的精准度上,classification tree模型亦优于logistics模型;将coarsetree和neuralnet模型的结果进行交叉互补时,可明显减少假阴性病例数。结论神经网络与决策树分类器相结合对结果预测的精准性远远高于传统的logistic模型。
Objective To explore the application of neural network model(NNM) in early warning of nosocomial infection(NI) for effective control of NI. Methods We extrated data on 4 911 inpatients with infections(139 NI and 4 776 non-NI) in a terciary grade A hospital during March 2017. A algorithm formula was established using NNM combined with decision tree classifier after training based on the data collected. Then the established algorithm formula was atopted to predicate the occurence of infection inpatients in the hospital in a specific duration and compared the predictions to those of actual occurences to develop an optimal core algorithm for analysis of data from hospital infection information system.Results For the models established, the fitting of classification tree was better than that of NNM and both the fitting of classification tree and NNM were vastly superior to that of logistic model. The predictive accuracy of classification tree model was better than that of logisitics model. The number of false negative prediction was obviously decreased with crosscomplementing of coarsetree model and neuralnet model. Conclusion In predication of NI occurence, the predictive accuracy of neural network model combined with classification tree model is obviously hgither than taht of conventional logistics model.
Objective To explore the application of neural network model(NNM) in early warning of nosocomial infection(NI) for effective control of NI. Methods We extrated data on 4 911 inpatients with infections(139 NI and 4 776 non-NI) in a terciary grade A hospital during March 2017. A algorithm formula was established using NNM combined with decision tree classifier after training based on the data collected. Then the established algorithm formula was atopted to predicate the occurence of infection inpatients in the hospital in a specific duration and compared the predictions to those of actual occurences to develop an optimal core algorithm for analysis of data from hospital infection information system.Results For the models established, the fitting of classification tree was better than that of NNM and both the fitting of classification tree and NNM were vastly superior to that of logistic model. The predictive accuracy of classification tree model was better than that of logisitics model. The number of false negative prediction was obviously decreased with crosscomplementing of coarsetree model and neuralnet model. Conclusion In predication of NI occurence, the predictive accuracy of neural network model combined with classification tree model is obviously hgither than taht of conventional logistics model.
引文
[1]王力红,朱士俊.医院感染学[M].北京:人民卫生出版社.2014:886-900.
[2]徐显荔,杨文,王定媚,等.某地区基层医疗机构医院感染管理现状[J].中国感染控制杂志,2017(10):971-972.
[3]李卫光,朱其凤,秦成勇,等.山东省医院感染管理部门设置现状调查[J].中华医院感染学杂志,2011(12):2526-2528.
[4]牟霞,徐艳,杨锦玲,等.贵州省医院感染管理部门设置现状调查分析[J].中华医院感染学杂志,2013(14):3465-3466,3469.
[5]吴明,靳桂明,魏华.医院感染管理部门应强化职能作用[J].中华医院感染学杂志,2007(11):1408-1410.
[6]张文彤,董伟.高等学校教材·SPSS统计分析高级教程(第2版)[M].北京:高等教育出版社出版社,2013:162-180.
[7]王小川,史峰,等.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社.2013:212-220,231-242.
[8]Kanimozhi CS,Anju P.Possibilistic LVQ neural network-an application to childhood autism grading[J].Neural Network World,2016,26(3):253-269.
[9]Bascil MS,Tesneli AY,Temurtas F.Spectral feature extraction of EEG signals and pattern recognition during mental tasks of 2-Dcursor movements for BCI using SVM and ANN[J].Australasian Physical and Engineering Sciences in Medicine September,2016,39(3):665-676.
[10]Lanzarini LC,Villa Monte A,Bariviera AF,et al.Simplifying credit scoring rules using LVQ+PSO[J].Kybernetes,2017,46(1):8-16.
[11]Podr?aj P,?ebular A.The application of LVQ neural network for weld strength evaluation of RF-welded plastic materials[J].IEEE/ASME Transactions on Mechatronics,2016,21(2):1063-1071.
[12]Sun TH,Tien FC,Tien FC,et al.Automated thermal fuse inspection using machine vision and artificial neural networks[J].Journal of Intelligent Manufacturing,2016,27(3):639-651.
[13]Zhang Z,Ming WY,Zhang GJ,et al.A new method for on-line monitoring discharge pulse in WEDM-MS proces[J].The International Journal of Advanced Manufacturing Technology,2015,81(5-8):1403-1418.
[14]罗建春,晁勤,罗洪,等.基于LVQ-GA-BP神经网络光伏电站出力短期预测[J].电力系统保护与控制,2014,42(13):89-94.
[15]崔明,乔兰,李远,等.LVQ神经网络在探地雷达成果解译中的应用[J].现代隧道技术,2013,50(6):19-23.
[16]叶晓波,王松.贝叶斯分类与LVQ神经网络分类性能对比研究[J].电脑与信息技术,2013,21(4):14-17.
[17]周云龙,李红延,李洪伟.改进的LVQ神经网络在风机故障诊断中的应用[J].化工自动化及仪表,2013,40(5):610-615.
[18]丁硕,常晓恒,巫庆辉,等.基于LVQ神经网络风电机组齿轮箱故障诊断研究[J].现代电子技术,2014,37(10):150-152.
[19]律方成,张波.LVQ神经网络在GIS局部放电类型识别中的应用[J].电测与仪表,2014,51(18):112-115.
[20]赵学观,王秀,李翠玲,等.基于主成分分析及LVQ神经网络的番茄种子品种识别[J].浙江农业学报,2017,29(8):1375-1383.
[21]牟霞,徐艳,张骥,等.依托信息化进行医院感染现患率调查[J].中华医院感染学杂志,2014,24(19):4887-4889.
[22]李毅志,邓银川,代剑.医院感染实时监控系统在质量改进中的应用[J].医疗卫生装备,2015,36(10):122-124.
[23]钟山.医院感染信息预警监测系统的设计与应用[J].中华医学图书情报杂志,2015,24(7):15-18.
[24]万艳春,李玉.医院感染管理信息系统的开发与应用[J].中国卫生质量管理,2015,22(2):70-72.
[25]刘卫方.基于医院数据平台的院感监测系统的构建与应用[J].江西通信科技,2015(1):38-43.
[2]徐显荔,杨文,王定媚,等.某地区基层医疗机构医院感染管理现状[J].中国感染控制杂志,2017(10):971-972.
[3]李卫光,朱其凤,秦成勇,等.山东省医院感染管理部门设置现状调查[J].中华医院感染学杂志,2011(12):2526-2528.
[4]牟霞,徐艳,杨锦玲,等.贵州省医院感染管理部门设置现状调查分析[J].中华医院感染学杂志,2013(14):3465-3466,3469.
[5]吴明,靳桂明,魏华.医院感染管理部门应强化职能作用[J].中华医院感染学杂志,2007(11):1408-1410.
[6]张文彤,董伟.高等学校教材·SPSS统计分析高级教程(第2版)[M].北京:高等教育出版社出版社,2013:162-180.
[7]王小川,史峰,等.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社.2013:212-220,231-242.
[8]Kanimozhi CS,Anju P.Possibilistic LVQ neural network-an application to childhood autism grading[J].Neural Network World,2016,26(3):253-269.
[9]Bascil MS,Tesneli AY,Temurtas F.Spectral feature extraction of EEG signals and pattern recognition during mental tasks of 2-Dcursor movements for BCI using SVM and ANN[J].Australasian Physical and Engineering Sciences in Medicine September,2016,39(3):665-676.
[10]Lanzarini LC,Villa Monte A,Bariviera AF,et al.Simplifying credit scoring rules using LVQ+PSO[J].Kybernetes,2017,46(1):8-16.
[11]Podr?aj P,?ebular A.The application of LVQ neural network for weld strength evaluation of RF-welded plastic materials[J].IEEE/ASME Transactions on Mechatronics,2016,21(2):1063-1071.
[12]Sun TH,Tien FC,Tien FC,et al.Automated thermal fuse inspection using machine vision and artificial neural networks[J].Journal of Intelligent Manufacturing,2016,27(3):639-651.
[13]Zhang Z,Ming WY,Zhang GJ,et al.A new method for on-line monitoring discharge pulse in WEDM-MS proces[J].The International Journal of Advanced Manufacturing Technology,2015,81(5-8):1403-1418.
[14]罗建春,晁勤,罗洪,等.基于LVQ-GA-BP神经网络光伏电站出力短期预测[J].电力系统保护与控制,2014,42(13):89-94.
[15]崔明,乔兰,李远,等.LVQ神经网络在探地雷达成果解译中的应用[J].现代隧道技术,2013,50(6):19-23.
[16]叶晓波,王松.贝叶斯分类与LVQ神经网络分类性能对比研究[J].电脑与信息技术,2013,21(4):14-17.
[17]周云龙,李红延,李洪伟.改进的LVQ神经网络在风机故障诊断中的应用[J].化工自动化及仪表,2013,40(5):610-615.
[18]丁硕,常晓恒,巫庆辉,等.基于LVQ神经网络风电机组齿轮箱故障诊断研究[J].现代电子技术,2014,37(10):150-152.
[19]律方成,张波.LVQ神经网络在GIS局部放电类型识别中的应用[J].电测与仪表,2014,51(18):112-115.
[20]赵学观,王秀,李翠玲,等.基于主成分分析及LVQ神经网络的番茄种子品种识别[J].浙江农业学报,2017,29(8):1375-1383.
[21]牟霞,徐艳,张骥,等.依托信息化进行医院感染现患率调查[J].中华医院感染学杂志,2014,24(19):4887-4889.
[22]李毅志,邓银川,代剑.医院感染实时监控系统在质量改进中的应用[J].医疗卫生装备,2015,36(10):122-124.
[23]钟山.医院感染信息预警监测系统的设计与应用[J].中华医学图书情报杂志,2015,24(7):15-18.
[24]万艳春,李玉.医院感染管理信息系统的开发与应用[J].中国卫生质量管理,2015,22(2):70-72.
[25]刘卫方.基于医院数据平台的院感监测系统的构建与应用[J].江西通信科技,2015(1):38-43.