Table 4.

Order of importance of predictors for the models.

Model		Importance rank
		1st	2nd	3rd	4th	5th	6th
MLRa
	Nob	Age	RBSc	BMI	CHOLd	Non-HDLe	eGFRf
RFg
	No	Age	RBS	BMI	eGFR	CHOL	Non-HDLh
	Yesh	RBS	Age	CHOL	eGFR	Non-HDL	BMI
LRi
	No	RBS	Age	Non-HDL	CHOL	BMI	eGFR
	Yes	RBS	Age	Non-HDL	eGFR	CHOL	BMI
SVMj (SHAPk & LIMEl)
	No	Age	RBS	BMI	Non-HDL	CHOL	eGFR
	Yes	RBS	Age	CHOL	Non-HDL	BMI	eGFR
MLPm (SHAP & LIME)
	No	RBS	Age	Non-HDL	CHOL	BMI	eGFR
	Yes	RBS	Age	eGFR	CHOL	Non-HDL	BMI

^aMLR: multiple logistic regression.

^bWithout longitudinal data.

^cRBS: random blood sugar.

^dCHOL: total cholesterol.

^enon-HDL: non–high-density lipoprotein.

^feGFR: estimated glomerular filtration rate.

^gRF: random forest.

^hWith longitudinal data.

ⁱLR: logistic regression.

^jSVM: support vector machine.

^kSHAP: Shapley Additive Explanations.

^lLIME: local interpretable model-agnostic explanations.

^mMLP: multilayer perceptron.