Skip to main content

Table 1 Publicly available datasets used for discovery of the 8-gene set and training of the 8-gene XGBoost model. Healthy controls, convalescent patients, and patients with other febrile illnesses were removed. Longitudinal samples were excluded for gene set discovery and model training but included for temporal gene expression analysis (included in “Total samples used”). WB, whole blood; PBMC, peripheral blood mononuclear cells

From: An 8-gene machine learning model improves clinical prediction of severe dengue progression

Dataset Platform Year Reference Country Age Tissue Samples used in discovery Total samples used
GSE40628 GPL16021 (Lymphochip) 2007 Simmons CP [25] Vietnam Adults WB 14 14
GSE18090 GPL570 (Affymetrix) 2009 Nascimento EJ [26] Brazil Adults PBMC 18 18
GSE13052 GPL2700 (Illumina) 2009 Long HT [27] Vietnam Children WB 18 18
GSE25001 GPL6104 (Illumina) 2010 Hoang LT [28] Vietnam Children/adults WB 96 168
GSE17924 GPL4133 (Agilent) 2010 Devignot S [29] Cambodia Children WB 48 48
GSE38246 GPL15615 (Illumina) 2012 Popper SJ [30] Nicaragua Children PBMC 41 102
GSE43777 GPL201 (Affymetrix) 2013 Sun P [31] Venezuela Children/adults PBMC 26 112
GSE43777 GPL570 (Affymetrix) 2013 Sun P [31] Venezuela Children/adults PBMC 20 74
GSE51808 GPL13158 (Affymetrix) 2014 Kwissa M [32] Thailand Adults WB 28 28
GSE94892 GPL16791 (Illumina) 2017 Banerjee A [14] India Children/adults PBMC 31 31
GSE100299 GPL17586 (Affymetrix) 2017 Simon-Lorière E [15] Cambodia Children PBMC 25 25
Total 365 638