Artificial Intelligence–Augmented Human Instruction and Surgical Simulation Performance
Bibliographic record
Abstract
Importance: How the Intelligent Continuous Expertise Monitoring System, an artificial intelligence tutoring system, might be best optimized for surgical training is unknown. Objective: To determine the effects of artificial intelligence-augmented personalized expert instruction vs intelligent tutoring alone on surgical performance, skill transfer, and affective-cognitive responses. Design, Setting, and Participants: This single-blinded randomized clinical trial was conducted among a volunteer sample of medical students in preparatory, first, or second year without prior use of a virtual reality surgical simulator (NeuroVR) at the McGill Neurosurgical Simulation and Artificial Intelligence Learning Centre in Montreal, Quebec, Canada. Cross-sectional data were collected from March to September 2024, and per-protocol data analysis was conducted in March 2025. Intervention: During simulated surgical procedures, trainees received 1 of 3 feedback methods. Group 1 received only intelligent tutor instruction (control). The 2 intervention arms included group 2, which received expert feedback in identical words to the intelligent tutor, and group 3, which received artificial intelligence data-informed personalized expert feedback. Main Outcomes and Measures: The coprimary outcomes included change in overall surgical performance across practice resections and skill transfer to a complex realistic scenario, measured by artificial intelligence-calculated composite expertise score (range, -1.00 [novice] to 1.00 [expert]). Secondary outcomes included emotional and cognitive demands, measured via questionnaires. Results: In this randomized clinical trial, the final analysis included 87 medical students (46 [53%] women; mean [SD] age, 22.7 [4.0] years), with 30, 29, and 28 participants in groups 1, 2, and 3, respectively. Group 3 achieved significantly higher scores than group 1 across several trials, including trial 5 (mean difference, 0.26; 95% CI, 0.09-0.43; P = .01) and the realistic task (mean difference, 0.20; 95% CI, 0.06-0.34; P = .02). Group 3 also achieved significantly better scores than the other 2 groups in certain metrics, such as bleeding and injury risk. Emotions and cognitive load demonstrated significant differences. Conclusions and Relevance: In this randomized clinical trial, personalized expert instruction resulted in enhanced surgical performance and skill transfer compared with intelligent tutor instruction, highlighting the importance of human input and participation in artificial intelligence-based surgical training. Trial Registration: ClinicalTrials.gov Identifier: NCT06273579.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".