Application of regression model combined with computer technology in the construction of early warning model of sepsis infection in children. Issue 2 (February 2020)

• Record Type: Journal Article
• Authors: Yang, Jing; Ma, Yujie; Mao, Min; Zhang, Pingli; Gao, Huixiang
• Is Part Of: Journal of infection and public health. Volume 13:Issue 2(2020)
• Page Start: 253
• Page End: 259
• Publication Date: 2020-02
• Subjects: Logistic regression analysis -- Computer technology -- Early warning model for children with sepsis; Communicable diseases -- Periodicals; Public health -- Periodicals; Epidemiology -- Periodicals; Nosocomial infections -- Prevention -- Periodicals; Medical microbiology -- Periodicals; 614.4
• DOI: 10.1016/j.jiph.2019.11.012
• Languages: English
• ISSNs: 1876-0341

Abstract

Abstract: This paper uses computer technology combined with regression model to analyze the risk factors of children with sepsis, determine the relevant factors and establish a corresponding early warning model of sepsis, and then verify the clinical application value of the regression model. The paper collected severe infections and sepsis in children who came to our hospital from 2014 to 2018, including 129 patients with infection and 86 patients with sepsis. The general conditions, clinical symptoms, laboratory tests and other factors were used. Analysis, to identify the risk of infection development into sepsis, and use Logistic regression model combined with computer technology to construct an early warning model of sepsis. The experimental results show that early warning of sepsis is closely related to skin spots, platelets, procalcitonin, creatinine and international normalized ratio. The experiment demonstrates that the early warning model has higher sensitivity and specificity, and has higher accuracy for predicting whether infection develops into sepsis in advance, and has certain clinical value.