Application of a decision tree model in the early identification of severe patients with severe fever with thrombocytopenia syndrome

• Published in: PloS one 2021-07, Vol.16 (7), p.e0255033-e0255033
• Main Authors: Wang, Bohao, He, Zhiquan, Yi, Zhijie, Yuan, Chun, Suo, Wenshuai, Pei, Shujun, Li, Yi, Ma, Hongxia, Wang, Haifeng, Xu, Bianli, Guo, Wanshen, Huang, Xueyong
• Format: Article
• Language: English
• Subjects: Analysis; Arachnids; Biology and Life Sciences; Body temperature; Computer and Information Sciences; Cough; Data mining; Decision trees; Decision-making; Demographics; Diagnosis; Disease control; Disease prevention; Engineering and Technology; Fatalities; Fever; Health aspects; Hypersomnia; Infectious diseases; Laboratories; Logistics; Mathematical models; Medicine and Health Sciences; Microorganisms; Nausea; Parameters; Pathogens; Patients; Public health; Research and Analysis Methods; Sample size; Signs and symptoms; Sleep disorders; Statistical analysis; Thrombocytopenia; Tremor
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0255033

Severe fever with thrombocytopenia syndrome (SFTS) is a serious infectious disease with a fatality of up to 30%. To identify the severity of SFTS precisely and quickly is important in clinical practice. From June to July 2020, 71 patients admitted to the Infectious Department of Joint Logistics Support Force No. 990 Hospital were enrolled in this study. The most frequently observed symptoms and laboratory parameters on admission were collected by investigating patients' electronic records. Decision trees were built to identify the severity of SFTS. Accuracy and Youden's index were calculated to evaluate the identification capacity of the models. Clinical characteristics, including body temperature (p = 0.011), the size of the lymphadenectasis (p = 0.021), and cough (p = 0.017), and neurologic symptoms, including lassitude (p