TABLE 5.

Evaluation metrics representing the performance of the GBM model classifying surgical expertise of participants performing blunt dissection, retraction, cold dissection, and burn dissection subtasks into 3 levels: inexperienced, competent, or experienced

Average % (Standard Deviation%)	Subtask 1: Blunt Dissection	Subtask 2: Retraction	Subtask 3: Cold Dissection	Subtask 4: Burn Dissection
Precision	92 (4)	96 (1)	94 (4)	96 (1)
Recall	95 (4)	96 (2)	96 (3)	96 (2)
F1-score	93 (4)	96 (1)	94 (3)	96 (2)
Accuracy	95 (3)	96 (1)	96 (2)	96 (2)