Surgical motor skill acquisition requires prolonged training and durable retention, yet standard behavioral metrics capture performance changes without revealing the neural mechanisms of learning. Here, we validate directed functional connectivity (dFC)—computed from electroencephalography across five cortical regions using nonlinear Granger causality—as a brain-based biomarker for tracking motor learning and retention. Twenty-five trainees completed a 15-day laparoscopic suturing program followed by six-week retention testing; an untrained control group (n = 27) and 15 expert surgeons served as behavioral and autonomous-stage references. dFC was evaluated using subtask-level decomposition, change-point detection, and a one-dimensional convolutional neural network benchmarked against the Fundamentals of Laparoscopic Surgery (FLS) score. dFC classified pre- versus post-training trials with 94.4% accuracy, outperforming the FLS-based classifier (84.5%), while matching FLS on pre- versus retention discrimination (87.5% vs. 88.5%). Notably, dFC identified the cognitive-to-associative transition one day later (day 6) than behavioral metrics (day 5), consistent with sleep-dependent neural consolidation. Neither measure changed further from post-training to retention, and controls exhibited no adaptation. Individual-level dFC measures tracked behavioral cumulative sum (CUSUM) trajectories. Overall, dFC provides a subtask-level, longitudinally stable biomarker of neural adaptation that complements behavioral metrics and holds potential for brain-informed surgical training.
The authors gratefully acknowledge the support of this work through the Medical Technology Enterprise Consortium (MTEC) award #W81XWH2090019, and the U.S. Army Futures Command, Combat Capabilities Development Command Soldier…
Source: npj Science of Learning — Read the full article on the original site ↗