Table 3.

The Model development processes and evaluations used in the included studies.

Type and study		Data preprocessing				Model optimization				Interpretation
		Numeric variables	Categorical variables	Missing data	Feature selection		Hyperparameter value selection	Generalizability consideration
Type 1b
	Sena et al [38]	Normalization	N/Aa	NRb	None		Software default	10-fold CVc	VId
	Nilsaz-Dezfouli et al [45]	NR	NR	NR	VI		Grid search	5×5-fold CV	VI
Type 2a
	Parikh et al [39]	NR	NR	Constant value imputation	Zero variance and between-variable correlation		Grid search	5-fold CV	VI and coefficient
	Klén et al [48]	NR	NR	Complete cases only	LASSOe LRf		NR	NR	VI
	Karhade et al [42]	NR	NR	missForest multiple imputation	RFg		NR	3×10-fold CV	VI, PDPh, and LIMEi
	Karhade et al [41]	NR	NR	Multiple imputation	Recursive feature selection		NR	10-fold CV	NR
	Arostegui et al [46]	Discretization	One-hot encoding	Constant value imputation	RF variable importance		Software default	Bootstrapping	VI and decision tree rules
	Bertsimas et al [50]	NR	NR	Optimal impute algorithm	None		NR	NR	VI and decision tree rules
	Chiu et al [49]	NR	NR	Complete cases only	Univariate Cox proportional hazard model		NR	NR	VI
	Zhang et al [40]	Normalization	One-hot encoding	NR	Forward stepwise selection algorithm		NR	10-fold CV	VI
	Biglarian et al [47]	NR	NR	NR	None		NR	NR	NR
Type 2b
	Elfiky et al [43]	NR	NR	Probabilistic imputation	None		Grid search	4-fold CV	VI
	Hanai et al [44]	Standardization	NR	NR	Between-variable correlation and PIMj		NR	5-fold CV	VI
Type 4
	Manz et al [37]	NR	NR	Constant value imputation	N/A		N/A	N/A	VI and coefficient
	Karhade et al [36]	NR	NR	missForest multiple imputation	N/A		N/A	N/A	NR

^aN/A: not applicable.

^bNR: not reported.

^cCV: cross-validation.

^dVI: variable importance.

^eLASSO: least absolute shrinkage and selection operator.

^fLR: logistic regression.

^gRF: random forest.

^hPDP: partial dependence plot.

ⁱLIME: local interpretable model-agnostic explanation.

^jPIM: parameter-increasing method.