Development and validation of three machine-learning models for predicting multiple organ failure in moderately severe and severe acute pancreatitis

Table 3 Different combinations of features by LRA

Combination of features No. of features	HCT	PT	APTT	TT	FIB	D-dimer	R-time	K-time	α	MA	CI	CRP	IL-6	PCT	BUN	Creatinine	AUC
1													√				0.7088
2					√											√	0.7803
3					√								√			√	0.8101
4					√			√					√			√	0.8226
5	√				√			√					√			√	0.8294
6	√		√		√			√					√			√	0.8319
7	√	√	√		√			√					√			√	0.8275
8	√	√			√			√		√		√	√			√	0.8269
9					√		√	√	√	√	√	√	√			√	0.8285
10		√			√	√	√		√	√	√	√	√			√	0.8240
11			√		√	√	√		√	√	√	√	√		√	√	0.8221
12			√		√	√	√	√	√	√	√	√	√		√	√	0.8147
13		√	√		√	√	√	√	√	√	√	√	√		√	√	0.8149
14	√	√	√		√		√	√	√	√	√	√	√	√	√	√	0.8054
15		√	√	√	√	√	√	√	√	√	√	√	√	√	√	√	0.8040
16	√	√	√	√	√	√	√	√	√	√	√	√	√	√	√	√	0.7833

ISSN: 1471-230X