MétaCan
Menu
Back to cohort
Record W4415781329 · doi:10.1038/s44387-025-00032-8

Combining real-time AI and in-person expert instruction in simulated surgical skills training - Randomized crossover trial

2025· article· en· W4415781329 on OpenAlexafffund
Recai Yilmaz, Ahmad Alsayegh, Mohamad Bakhaidar, Ali M. Fazlollahi, Nour Abou Hamdan, Trisha Tee, Albert Shalmiev, Denis Laroche, Carlo Santaguida, Daniel A. Donoho, Rolando F. Del Maestro

Bibliographic record

Venuenpj Artificial Intelligence · 2025
Typearticle
Languageen
FieldMedicine
TopicSurgical Simulation and Training
Canadian institutionsNational Research Council CanadaMcGill University Health CentreMcGill UniversityMontreal Neurological Institute and HospitalArtificial Intelligence in Medicine (Canada)
FundersFonds de Recherche du Québec - SantéMontreal Neurological Institute and HospitalBrain Tumour Foundation of CanadaRoyal College of Physicians and Surgeons of CanadaMcGill UniversityFaculty of Medicine, McGill UniversityCongress of Neurological Surgeons
KeywordsRandomized controlled trialCrossover studyCurriculumDreyfus model of skill acquisitionEducational measurementMEDLINECrossoverExpert opinion

Abstract

fetched live from OpenAlex

Abstract Traditional surgical training has significant limitations, lacking objectivity and standardization. Deploying AI tools with conventional expert-mediated teaching may uncover areas where AI could complement experts and enhance surgical training through real-time performance assessment and feedback alongside risk mitigation. This randomized crossover trial assessed learning outcomes in two training sessions involving in-person expert instruction and real-time AI feedback using previously validated tumor resection simulations. Receiving expert feedback before real-time AI instruction led to greater performance improvement in trainee performance scores compared to the opposite order, with a mean difference of 0.67 95%CI [0.43–0.91], p < 0.001. Diminishing returns were observed with human expert feedback, which were not seen with AI feedback, such as increased injury and bleeding risk. In surgical procedural training, AI feedback may efficiently maintain peak performance after an initial learning phase led by human experts. AI-integrated surgical curricula should consider the relative benefits of both AI and expert feedback.

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 imitation

Not 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.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.008
Threshold uncertainty score0.036

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.010
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0050.002
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.002
Open science0.0020.001
Research integrity0.0040.004
Insufficient payload (model declined to judge)0.0080.001

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.

Opus teacher head0.052
GPT teacher head0.368
Teacher spread0.316 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designRandomized trial
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

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same venuenpj Artificial IntelligenceSame topicSurgical Simulation and TrainingFrench-language works237,207