Table 2.

Models for favorable outcome (paradigm I).

Scenario	GLM	Lasso	ElasticNet	Catboost	MLP	SVMC	Naive bayes
I A	0.65	0.65	0.6	0.67	0.67	0.6	0.65
I A+B	0.62*	0.64*	0.6	0.64*	0.64*	0.57	0.63*
I A+B+C	0.71*+	0.71*+	0.68*+	0.73*+	0.7*+	0.67*+	0.69*+

The prediction variable sets (Table 1) were used to predict a favorable outcome (mRS dichotomized as 0–2 vs. 3–6). The addition of thrombectomy-associated variables (set C) leads to a noticeable improvement of all machine learning models. Highest AUC results for each variable set are marked in bold. Confidence intervals for all models are included in the Supplementary Material. Statistically significant difference in model performance between variable sets are marked with * and + to signal difference from A and from A+B, respectively. Significance was determined by a value of p lower than 0.05, resulting from the Wilcoxon signed-rank test.