PROBAST: Prediction model  Risk Of Bias ASsessment Tool

Step 1: Specify your  systematic review question(s) – not applicable.

Step 2: Classify the type of prediction  model evaluation – development and validation.

Step 3: Assess risk of  bias and applicability

Risk of Bias
Participants	Predictors	Outcome	Analysis
Were appropriate data sources used, e.g., cohort, RCT, or nested case–control study data? Yes	Were predictors defined and assessed in a similar way for all participants? Yes	Was the outcome determined appropriately? Yes	Were there a reasonable number of participants with the outcome? Yes
Were all inclusions and exclusions of participants appropriate? Yes	Were predictor assessments made without knowledge of outcome data? Yes	Was a prespecified or standard outcome definition used? Yes	Were continuous and categorical predictors handled appropriately? Yes
	Are all predictors available at the time the model is intended to be used? Yes	Were predictors excluded from the outcome definition? Yes	Were all enrolled participants included in the analysis? No
		Was the outcome defined and determined in a similar way for all participants? Yes	Were participants with missing data handled appropriately? Yes
		Was the outcome determined without knowledge of predictor information? Yes	Was selection of predictors based on univariable analysis avoided? No
		Was the time interval between predictor assessment and outcome determination appropriate? Yes	Were complexities in the data (e.g., censoring, competing risks, sampling of control participants) accounted for appropriately? Yes
			Were relevant model performance measures evaluated appropriately? Yes
			Were model overfitting, underfitting, and optimism in model performance accounted for? Yes
			Do predictors and their assigned weights in the final model correspond to the results from the reported multivariable analysis? Yes

ROB = risk of bias. + indicates low ROB/low concern regarding applicability; − indicates high ROB/high concern regarding applicability; and ? indicates unclear ROB/unclear concern regarding applicability.