{"id":"W4283258651","doi":"10.36227/techrxiv.20085425.v1","title":"Multi-modal Deep Learning for Assessing Surgeon Technical Skill on a Surgical Knot-tying Task","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Knot tying; Artificial intelligence; Tying; Computer science; Task (project management); Modal; Machine learning; Deep learning; Intraclass correlation; Correlation coefficient; Statistics; Mathematics; Engineering; Surgery; Medicine; Psychometrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001837079,0.001303873,0.000427607,0.0006720931,0.0002637156,0.0006411527,0.0009492542,0.00132442,0.001479825],"category_scores_gemma":[0.004578517,0.0002694381,0.0007189675,0.00046711,0.0003857371,0.000859896,0.001117532,0.001523939,0.0007240577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009280586,"about_ca_system_score_gemma":0.0008031428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008173092,"about_ca_topic_score_gemma":0.01315518,"domain_scores_codex":[0.9991709,0.0002633169,0.00004743972,0.0002375468,0.0001830181,0.00009783537],"domain_scores_gemma":[0.9986627,0.0006028739,0.0001205516,0.0001984188,0.0003148057,0.0001005981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001459509,0.001577072,0.02079893,0.0005208484,0.0004501753,0.0003548771,0.0004462785,0.31888,0.04536155,0.001370808,0.01916758,0.5896125],"study_design_scores_gemma":[0.00003884167,0.0003284058,0.01210963,0.0000417055,0.00005238105,0.0001167762,0.00008408047,0.9705915,0.01285353,0.001961596,0.001772141,0.00004944906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6866977,0.001705998,0.2948803,0.0007592782,0.0004004553,0.0004442298,0.004998833,0.005371747,0.004741416],"genre_scores_gemma":[0.9076552,0.0002844263,0.08088895,0.0002847384,0.00005467451,0.000284537,0.00630442,0.000105355,0.004137642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008173092,"threshold_uncertainty_score":0.01625103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06339730988557597,"score_gpt":0.3840572587635652,"score_spread":0.3206599488779892,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}