Risk prediction of hyperuricemia based on particle swarm fusion machine learning solely dependent on routine blood tests

Table 3 Multivariate logistic regression analysis of hyperuricemia

Indicators	Coef	Std_err	Z	P	95%CI
CONST	4.868	6.625	0.735	0.462	[−8.117 17.854]
HGB	−0.003	0.006	−0.416	0.677	[−0.015 0.010]
LYM	−0.133	0.069	−1.934	0.053	[−0.269 0.002]
NEUT%	−0.155	0.074	−2.093	0.036	[−0.299 − 0.010]
ANC	0.477	0.126	3.782	0.000	[0.230 0.724]
MONO#	−1.804	1.144	−1.577	0.115	[−4.047 0.438]
BASO#	−0.454	3.439	−0.132	0.895	[−7.194 6.286]
EOS#	−1.724	1.126	−1.532	0.126	[−3.930 0.482]
RDW-CV	0.021	0.007	3.059	0.002	[0.008 0.035]
AGE	0.037	0.008	4.640	0.000	[0.021 0.052]
SEX	−0.428	0.238	−1.799	0.072	[−0.894 0.038]
WEIGHT	0.031	0.007	4.425	0.000	[0.017 0.045]

ISSN: 1472-6947