Effectiveness of early warning management of nosocomial infection based on neural network model and decision tree model
10.3969/j.issn.1006-2483.2023.05.019
- VernacularTitle:神经网络模型联合决策树模型预警医院感染的管理效力
- Author:
Xiaojuan LIU
1
;
Liyan JIAO
1
;
Xiaoxue SHI
1
;
Yuping CHEN
1
Author Information
1. Infection Management Office of Affiliated Hospital of Hebei University of Engineering Hospital , Handan , Hebei 056000 , China
- Publication Type:Journal Article
- Keywords:
Neural network model;
Decision tree model;
Hospital infection;
Early warning
- From:
Journal of Public Health and Preventive Medicine
2023;34(5):87-90
- CountryChina
- Language:Chinese
-
Abstract:
Objective To predict the effectiveness of nosocomial infection management and effectively control the risk of nosocomial infection. Methods In this study, with the population of ICU patients in a Grade A hospital , 345 ICU patients seen from June 2020 to June 2021 were included in the analysis to collect the infection data in the hospital. Based on the use of the decision tree model to analyze the influencing factors of nosocomial infection, the neural network model was also used to predict the risk of developing nosocomial infection. Results The decision tree model showed that advanced age (age> 80 years) influenced the root node. Type 2 diabetes, gender by male, and BMI level were child nodes, which had different synergistic effects on the occurrence of nosocomial infection. At the same time, random forest (RF), support vector machine (SVM), logical regression (LR) and K nearest neighbor (KNN) algorithms were used to construct a neural network prediction model of nosocomial infection risk, suggesting that the condition, sex and body size of basic diseases are related to the occurrence of nosocomial infection. The combined use of the above model in parallel can effectively increase the specificity and reduce the missed diagnosis. Conclusion The neural network model joint decision tree model in parallel and joint early warning of nosocomial infection risk have excellent effect, and can effectively provide information support for the prevention, management and disposal of nosocomial infection.