P.140 Development and predictive validation of an intelligent surgical bimanual skills continuous assessment system
Bibliographic record
Abstract
Background: Surgeons’ bimanual dexterity may correlate with the surgical outcome. Continuous assessment of psychomotor performance enables action-oriented feedback and error avoidance guidance. We outline an artificial intelligence (AI) application to continuously assess surgical bimanual skills and its predictive validation on surgical trainee performance throughout a neurosurgery residency program. Methods: Participants (n=50, 14 experts/neurosurgeons, 14 senior residents, 10 junior residents, 12 novices/medical students) performed two simulated subpial tumour resections a total of 300 times. A deep neural network was developed using expert/neurosurgeon and novice/medical student data to score bimanual performance at 0.2-second intervals between a score of 1.00 and -1.00. An average score was calculated for each task. Results: The average performance score differentiated among four expertise levels, p<.001. Neurosurgeons scored significantly higher than senior residents (p=.045) and junior residents scored significantly higher than medical students (p=.04). The intelligent system also differentiated between senior and junior trainee levels (p=.004). The performance score linearly correlated with resident year of neurosurgical training (adjusted R2=27.7%). Conclusions: The AI-powered intelligent system outlined is the first expert surgeon-data-based technical skills continuous assessment system, with predictive validity throughout a neurosurgical residency program. Intelligent systems may aid in the competency-based approach in surgery by accurately assessing trainee skills.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".