1247 Expert Surgeon-Level OSATS Rating Using Machine Learning for Surgical Performance Assessment
Bibliographic record
Abstract
INTRODUCTION: Real-time feedback can improve surgical skills, but current gold-standard approaches based on expert-provided Objective Structured Assessment of Technical Skills (OSATS) ratings are time-consuming, impractical, and unavailable to most surgeons and trainees. An artificial intelligence (AI) system can provide real-time, automated OSATS ratings which could bridge this gap. METHODS: Data from 532 tasks were recorded during medical students’ brain tumor surgery simulation training at the Neurosurgical Simulation and Artificial Intelligence Learning Centre, McGill University. These videos were rated by two blinded experts using OSATS. This data was split into three: training, validation, and testing datasets, for the development and independent verification in training the algorithm. A long short-term memory network was trained. RESULTS: Despite variations between expert ratings (cohen’s weighted kappa = .09), our machine learning algorithm achieved 78% accuracy overall and 79% accuracy in independent testing in differentiating between good and poor performance. The algorithm achieved 73% accuracy in predicting the OSATS ratings within a one-point range. CONCLUSIONS: Our work presents an automated real-time AI system that replicates expert decisions in surgical performance assessment. Provided with enough examples of good and poor surgical performance, machine learning systems may learn and emulate experts’ opinions. These systems may provide real-time expert-level feedback during procedures to inform the trainees about poor performance, help mitigate risks, and improve operative outcomes.
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 | 0.007 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".