Prediction of fatal adverse prognosis in patients with fever-related diseases based on machine learning: a retrospective study.

CONCLUSIONS: The main clinical indicators of concern included CTnT, RR, SPO2, T, ALB, and K. The bagging model and logistic regression model had better diagnostic performance comprehesively. Those may be conducive to the early identification of critical patients with fever by physicians.
PMID: 32044816 [PubMed - as supplied by publisher]

Source: Chinese Medical Journal - February 6, 2020 Category: General Medicine Authors: Zhao CH, Wu HT, Che HB, Song YN, Zhao YZ, Li KY, Xiao HJ, Zhai YZ, Liu X, Lu HX, Li TS Tags: Chin Med J (Engl) Source Type: research