SP2.1.1Continuous Monitoring and Assessment of Surgical Technical Skills Using Deep Learning
Bibliographic record
Abstract
Abstract Aims Excellent surgical technical skills are of paramount importance to perform surgical procedures, safely and efficiently. Virtual reality surgical simulators can both simulate real operations while providing standardized, risk-free surgical hands-on experience. The integration of AI (artificial intelligence) and virtual reality simulators provides opportunities to carry out comprehensive continuous assessments of surgical performance. We developed and tested a deep learning algorithm which can continuously monitor and assess surgical bimanual performance on virtual reality surgical simulators. Methods Fifty participants from four expertise levels (14 experts/neurosurgeons, 14 senior residents, 10 junior residents, 12 medical students) performed a simulated subpial tumor resection 5 times and a complex simulated brain tumor operation once on the NeuroVR platform. Participants were asked to remove the tumors completely while minimizing bleeding and damage to surrounding tissues employing a simulated ultrasonic aspirator and bipolar forceps. A deep neural network continually tracked the surgical performance utilizing 16 performance metrics generated every 0.2-seconds. Results The deep neural network was successfully trained using neurosurgeons and medical students’ data, learning the composites of expertise comparing high and lower skill levels. The trained algorithm was able to score the technical skills of individuals continuously at 0.2-second intervals. Statistically significant differences in average scores were identified between the 4 groups. Conclusions AI-powered surgical simulators provide continuous assessment of bimanual technical skills during surgery which may further define the composites necessary to train surgical expertise. To our knowledge, this is the first attempt in surgery to continuously assess surgical technical skills using deep learning.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".