TABLE 2.

PLS component coefficients and feature statistics

Structural connection	Loadings	VIP	Mean (SD)	Range
G_Supramarginal‐4↔G_SupraMarginal‐2	0.35	1.1	2.12 (3.28)	13.22
G_Temporal_Sup‐4↔S_Precentral‐6	0.34	1.09	0.01 (0.03)	0.15
G_Temporal_Sup‐4↔S_Precentral‐3	0.33	1.05	0.01 (0.03)	0.14
S_Intraparietal‐3↔S_Intraparietal‐2	0.32	1.02	18.89 (15.04)	73.28
G_Temporal_Sup‐4↔S_Precentral‐2	0.32	1	0.02 (0.04)	0.23
S_Sup_Temporal‐4↔S_Precentral‐6	0.31	0.96	0.02 (0.05)	0.26
G_Rolandic_Oper‐1↔G_Supramarginal‐1	0.3	0.96	1.12 (2.38)	9.04
G_SupraMarginal‐5↔G_SupraMarginal‐2	0.3	0.94	1.5 (3.03)	17.96
S_Intraparietal‐3↔S_Intraparietal‐1	0.3	0.94	9.01 (9.41)	38.73
S_Intraparietal‐2↔G_Angular‐1	0.29	0.9	5.35 (6.55)	28.08

Note: PLS component coefficients and feature statistics. Loadings and variable importance in projection (VIP) coefficients of the principal component resulting from the partial least squares (PLS) model fit on the optimal 10 features across the entire dataset (n = 71). Means, standard deviations, and ranges are also reported for each individual feature.