Author: Xiaofan Lu; Yang Wang; Taige Chen; Yongsheng Li; Jun Wang; Fangrong Yan
Title: Classification of COVID-19 in intensive care patients: towards rational and effective clinical triage Document date: 2020_4_11
ID: 6cr9h7no_5
Snippet: Data magnitude was manually checked and logarithmic transformation was utilized as appropriate; continuous data were further median-centered and scaled for being comparable. Binomial and Gaussian distributions were considered for categorical and continuous variables, respectively, and prior probability for the indicator variable gamma was set to 0.5 for each data category. Appropriate number of clusters was determined by minimizing the Bayesian i.....
Document: Data magnitude was manually checked and logarithmic transformation was utilized as appropriate; continuous data were further median-centered and scaled for being comparable. Binomial and Gaussian distributions were considered for categorical and continuous variables, respectively, and prior probability for the indicator variable gamma was set to 0.5 for each data category. Appropriate number of clusters was determined by minimizing the Bayesian information criterion. Only features with high posterior probability (e.g., 0.8) were kept. All statistical analyses were conducted with R3.6.2 using a Fisher's exact test for categorical data and a Kruskal-Wallis test for multiple group comparison; Survival rates was generated by Kaplan-Meier curve and analyzed with log-rank test. For unadjusted comparisons, a two-sided P<0.05 was considered statistically significant. All rights reserved. No reuse allowed without permission. the author/funder, who has granted medRxiv a license to display the preprint in perpetuity.
Search related documents:
Co phrase search for related documents- continuous categorical variable and exact test: 1
- exact test and group comparison: 1, 2, 3, 4
Co phrase search for related documents, hyperlinks ordered by date