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

Table 6 Performance comparison of optimization algorithms applied to XGBoost

optimization	Auc	Acc	P	R	F1	parameters
PSO	0.997	0.973	0.975	0.971	0.973	n_particles = 10,c₁ = 0.5,c₂ = 0.3,w = 0.9,max_iters = 100
GridSearch	0.997	0.972	0.970	0.976	0.976	scoring = f1,cv = 5,n_jobs = − 1,verbose = 1
GA	0.996	0.969	0.969	0.968	0.968	n = 10,max_gen = 100,pc = 0.7,pm = 0.2

ISSN: 1472-6947