Table 4.

Comparison of the average performance matrix and confusion matrix from five-fold cross-validation for (A) Individual top 10 feature, (B) Combined top 1 to 10 features.

(A)
Features	AUC	Accuracy	Precision	Recall	F1 Score	Specificity
Age	0.81	0.85 ± 0.04	0.86 ± 0.03	0.85 ± 0.04	0.85 ± 0.04	0.56 ± 0.05
Lymphocyte count	0.71	0.72 ± 0.10	0.75 ± 0.08	0.72 ± 0.06	0.72 ± 0.07	0.55 ± 0.17
D-Dimer	0.65	0.66 ± 0.08	0.67 ± 0.13	0.66 ± 0.04	0.65 ± 0.07	0.80 ± 0.14
Creatinine	064	0.62 ± 0.02	0.64 ± 0.02	0.62 ± 0.08	0.61 ± 0.06	0.80 ± 0.04
CRP	0.61	0.57 ± 0.05	0.57 ± 0.05	0.57 ± 0.04	0.57 ± 0.04	0.59 ± 0.09
HTN	0.61	0.65 ± 0.04	0.65 ± 0.04	0.65 ± 0.13	0.65 ± 0.07	0.66 ± 0.10
Kidney	0.60	0.54 ± 0.09	0.54 ± 0.08	0.54 ± 0.11	0.54 ± 0.09	0.50 ± 0.10
Heart	0.60	0.61 ± 0.09	0.69 ± 0.06	0.61 ± 0.06	0.56 ± 0.06	0.28 ± 0.14
Abs Neutrophil	0.59	0.61 ± 0.011	0.62 ± 0.09)	0.61 ± 0.014	0.60 ± 0.10	0.48 ± 0.14
GI_Symp	0.58	0.57 ± 0.03	0.57 ± 0.03	0.57 ± 0.05	0.56 ± 0.04	0.71 ± 0.03
(B)
Features	Overall Accuracy	Weighted Performance with 95% CI				Confusion Matrix
						Death		Alive
		Precision	Recall	F 1 Score	Specificity	TP	FP	FN	TN
Top 1 feature	0.85 ± 0.04	0.86 ± 0.03	0.85 ± 0.04	0.85 ± 0.04	0.56 ± 0.05	25	24	34	301
Top 2 features	0.91 ± 0.03	0.92 ± 0.03	0.91 ± 0.03	0.91 ± 0.03	0.76 ± 0.04	36	13	22	313
Top 3 features	0.91 ± 0.03	0.92 ± 0.03	0.91 ± 0.03	0.91 ± 0.03	0.78 ± 0.04	37	12	22	313
Top 4 features	0.9 ± 0.03	0.91 ± 0.03	0.9 ± 0.03	0.9 ± 0.03	0.74 ± 0.04	35	14	24	311
Top 5 features	0.92 ± 0.03	0.93 ± 0.02	0.92 ± 0.03	0.93 ± 0.03	0.83 ± 0.04	40	9	20	315
Top 6 features	0.92 ± 0.03	0.93 ± 0.03	0.92 ± 0.03	0.92 ± 0.03	0.81 ± 0.04	39	10	21	314
Top 7 features	0.91 ± 0.03	0.92 ± 0.03	0.91 ± 0.03	0.91 ± 0.03	0.78 ± 0.04	37	12	23	312
Top 8 features	0.91 ± 0.03	0.92 ± 0.03	0.91 ± 0.03	0.92 ± 0.03	0.8 ± 0.04	38	11	22	313
Top 9 features	0.92 ± 0.03	0.93 ± 0.03	0.92 ± 0.03	0.92 ± 0.03	0.8 ± 0.04	38	11	20	315
Top 10 features	0.91 ± 0.03	0.92 ± 0.03	0.91 ± 0.03	0.92 ± 0.03	0.78 ± 0.04	37	12	21	314