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

Table 9 Comparison with state-of-the-art methods

Papers	Feature optimization	Number of features	Classifier	Accuracy	AUC	XAI
Hou et al. [4]	Lr analysis	15	SVM	0.819	0.875	No
Zheng et al. [27]	LASSO	6	XGBoost	0.881	0.733	No
Zeng et al. [28]	Lr analysis	14	ANN	0.800	0.814	No
Ma [9]	Lr analysis	10	Bayesian	-	0.740	No
Yang [11]	LASSO	4	Lr	0.726	0.813	No
Chen et al. [49]	-	14	XGBoost	0.730	0.820	No
Gao et al. [5]	-	21	Rf	-	0.739(male)	No
					0.818(Female)
Proposed model	Lr analysis	7	Stacking	0.978	0.978	Yes

ISSN: 1472-6947