MétaCan
Menu
Back to cohort
Record W3158852312 · doi:10.1093/bjs/znab117.051

O51: ARTIFICIAL INTELLIGENCE UTILIZING RECURRENT NEURAL NETWORKS TO CONTINUOUSLY MONITOR COMPOSITES OF SURGICAL EXPERTISE

2021· article· en· W3158852312 on OpenAlexaff
Recai Yilmaz, Alexander Winkler-Schwartz, Nykan Mirchi, Aiden Reich, Rolando F. Del Maestro

Bibliographic record

VenueBritish journal of surgery · 2021
Typearticle
Languageen
FieldMedicine
TopicSurgical Simulation and Training
Canadian institutionsMcGill University
Fundersnot available
KeywordsVirtual realityTask (project management)MedicineArtificial neural networkSimulationComputer scienceArtificial intelligence

Abstract

fetched live from OpenAlex

Abstract Introduction Many surgical adverse events occur secondary to technical errors related to poor bimanual skills, fatigue and lack of the required expertise. We developed AI algorithms to continuously assess surgical bimanual technical performance during virtual reality simulated surgical tasks. To our knowledge, this is the first attempt in surgery to train AI algorithms to continuously monitor and evaluate bimanual skills comprehensively. Method Fifty individuals from four expertise levels (14 experts/neurosurgeons, 14 senior residents, 10 junior residents, 12 medical students) performed two virtual reality simulated surgical tasks with haptic feedback: a subpial tumor resection 5 times and a complex, realistically simulated brain tumor operation once. Each task required complete tumor removal while minimizing bleeding and damage to surrounding tissues using a simulated ultrasonic aspirator and a bipolar. A recurrent neural network continually tracked individual bimanual performance utilizing 16 performance metrics generated every 0.2 seconds. Result The recurrent neural network algorithm was successfully trained using neurosurgeons and medical students' data, learning the composites of expertise comparing high and lower skill levels. The trained algorithm outlined and monitored technical skills every 0.2 second continuously organizing performance of each surgical task into three levels: ‘excellent’, ‘average’ and ‘poor’. The percentage time spent on each level was calculated and significant differences found between all four groups for ‘excellent’ and ‘poor’ levels. Conclusion AI-powered surgical simulators provide an advanced assessment and training tool. AI's ability to continuous assess bimanual technical skills during surgery may further define the composites necessary to train surgical expertise. Abbrev AI: artificial intelligence Take-home message By advanced artificial intelligence algorithms surgeon's bi-manual technical skills can be assessed continuously, time periods of poor performance which increase the possibility of errors in performance can be identified.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.958
Threshold uncertainty score0.507

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.084
GPT teacher head0.326
Teacher spread0.242 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

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".

Quick stats

Citations2
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueBritish journal of surgerySame topicSurgical Simulation and TrainingFrench-language works237,207