{"id":"W4283266249","doi":"10.36227/techrxiv.20085425","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":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Knot tying; Artificial intelligence; Computer science; Tying; Task (project management); Modal; Deep learning; Machine learning; Correlation coefficient; Intraclass correlation; Statistics; Engineering; Mathematics; Surgery; Medicine","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":[0.001641503,0.00123441,0.0003957936,0.0005864705,0.0002428193,0.0005923666,0.0009201404,0.001278048,0.001623313],"category_scores_gemma":[0.003967481,0.0002611079,0.0006840667,0.0004112194,0.0003690242,0.0007990585,0.001028378,0.001433054,0.0007152512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009092795,"about_ca_system_score_gemma":0.0007729531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009285368,"about_ca_topic_score_gemma":0.01380333,"domain_scores_codex":[0.9992932,0.0002177982,0.00003812712,0.0002167696,0.0001440786,0.00009011465],"domain_scores_gemma":[0.9989127,0.0004850767,0.00009772833,0.000162533,0.0002467355,0.0000952155],"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":[0.00134335,0.001430392,0.01574736,0.0004165851,0.0003752637,0.0003303036,0.000375855,0.3435777,0.03785841,0.001273319,0.01932344,0.577948],"study_design_scores_gemma":[0.00003038902,0.0002592974,0.008338625,0.00003075443,0.00003821465,0.00007638861,0.00005838241,0.9787982,0.009613042,0.00145814,0.001262451,0.00003605587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7132663,0.001566382,0.2683573,0.0008235426,0.0004443703,0.0003975008,0.004625604,0.005307712,0.005211307],"genre_scores_gemma":[0.9159241,0.0002679839,0.07234079,0.0002768096,0.00005681333,0.0002399953,0.005897553,0.0001059583,0.004889992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009285368,"threshold_uncertainty_score":0.0184626,"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."}}