{"id":"W2974089311","doi":"10.2106/jbjs.18.01197","title":"Artificial Intelligence Distinguishes Surgical Training Levels in a Virtual Reality Spinal Task","year":2019,"lang":"en","type":"article","venue":"Journal of Bone and Joint Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal General Hospital; Montreal Neurological Institute and Hospital","funders":"","keywords":"Virtual reality; Artificial intelligence; Machine learning; Computer science; Support vector machine; Task (project management); Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002942357,0.0001215951,0.0009015374,0.0003275851,0.00003497374,0.00003000422,0.00001412442,0.00008488933,0.000252387],"category_scores_gemma":[0.00106541,0.00009441299,0.0002816706,0.0002327612,0.0000711301,0.0001236913,0.00002072683,0.0004036497,0.000008706238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003609237,"about_ca_system_score_gemma":0.0001650747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001503647,"about_ca_topic_score_gemma":0.000004633612,"domain_scores_codex":[0.9978099,0.00009931527,0.001342096,0.0001565728,0.0003579065,0.0002341989],"domain_scores_gemma":[0.9984615,0.0007256946,0.000408046,0.00008597202,0.0001113218,0.0002074067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00358517,0.0004626096,0.1589132,0.0001750182,0.0001045372,0.005655854,0.001886707,0.0003599671,0.001063603,0.002729216,0.00008068233,0.8249835],"study_design_scores_gemma":[0.001966951,0.001127338,0.9650964,0.003131829,0.00009312657,0.004591193,0.004144903,0.004575663,0.0008493629,0.003815427,0.01012653,0.000481274],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966744,0.0002360744,0.000397521,0.0009779861,0.0003148571,0.00006943887,0.000002015716,0.00001039752,0.001317285],"genre_scores_gemma":[0.9992824,0.00004804094,0.00007900031,0.0001453169,0.0003862413,5.701146e-7,0.000002082792,0.000009694793,0.00004666449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8245022,"threshold_uncertainty_score":0.385005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1712569808139496,"score_gpt":0.3443412334780411,"score_spread":0.1730842526640915,"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."}}