Table 2.

CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) checklist.

Author	Data source (description)	Outcome mortality	Data preparation		Model training				Predictive performance					Generalizability
			Aa	Bb	Cc	Dd	Ee	Ff		Gg	Hh	Ii	Jj		Kk	Ll	Mm	Nn
Pirracchio et al [1]	MIMICo 2	Hospital				✓	✓	✓		✓			✓			✓		✓
Nielsen et al [24]	Danish ICUp	Hospital 30/90 days	✓	✓	✓	✓	✓			✓	✓		✓				✓
Nimgaonkar et al [25]	ICU India	Hospital				✓	✓	✓		✓
Xia et al [26]	MIMIC 3	28 days/hospital	✓	✓		✓	✓			✓	✓						✓	✓
Purushotham et al [27]	MIMIC 3	Hospital, 2 days, 3 days, 30 days, 1 year	✓	✓		✓	✓			✓	✓		✓				✓	✓
Nanayakkara et al [28]	ANZICSq	Hospital	✓	✓	✓	✓	✓	✓		✓	✓				✓	✓	✓	✓
Meyer et al [29]	Germany	Hospital		✓		✓	✓			✓	✓		✓			✓		✓
Meiring et al [7]	CCHICr United Kingdom	Hospital	✓	✓	✓	✓	✓			✓							✓	✓
Lin et al [30]	MIMIC 3	Hospital	✓	✓		✓	✓	✓		✓	✓
Krishnan et al [31]	MIMIC 3	ICU	✓	✓		✓	✓			✓	✓					✓
Kang et al [32]	Korea	Hospital	✓		✓	✓	✓	✓		✓	✓				✓
Johnson et al [33]	United Kingdom	ICU and hospital	✓	✓		✓	✓	✓		✓		✓	✓			✓
Holmgren et al [34]	Sweden	Hospital and 30 days			✓	✓	✓	✓		✓	✓						✓	✓
Garcia-Gallo et al [35]	MIMIC 3	Hospital and 1 year	✓	✓	✓	✓	✓	✓		✓	✓						✓	✓
El-Rashidy et al [36]	MIMIC 3	ICU and hospital	✓	✓		✓	✓			✓	✓		✓				✓	✓
Silva et al [37]	EURICUSs 2	ICU	✓	✓	✓	✓	✓			✓	✓	✓			✓	✓
Caicedo-Torres et al [38]	MIMIC 3	ICU	✓	✓		✓	✓			✓	✓				✓
Deshmukh et al [39]	eICU-CRDt	ICU	✓	✓	✓	✓	✓			✓	✓				✓		✓
Ryan et al [40]	MIMIC 2	ICU and hospital	✓	✓	✓	✓	✓			✓	✓		✓				✓	✓
Mayaud et al [41]	MIMIC 2	Hospital	✓	✓		✓	✓	✓		✓		✓

^aData normalization/outlier addressed.

^bMissing data addressed.

^cHyperparameter optimization addressed.

^dOverfitting/shrinkage and cross-validation addressed.

^ePredictor selection, full model versus backward elimination.

^fCalibration assessed (Brier, Hosmer-Lemeshow, and calibration plot).

^gDiscrimination/reclassification performed (net reclassification improvement/integrated discrimination improvement).

^hClassification reported.

ⁱRecalibration performed.

^jExternally validated.

^kExplainability addressed/decision curve analysis.

^lClinical applicability addressed.

^mPrediction span defined.

ⁿIntended moment of use reported.

^oMIMIC: Medical Information Mart for Intensive Care.

^pICU: intensive care unit.

^qANZICS: Australia New Zealand Intensive Care Unit Society.

^rCCHIC: Critical Care Health Informatics Collaborative.

^sEURICUS: European ICU studies.

^teICU CRD: Electronic ICU Collaborative Research Database.