{"id":"W4402260351","doi":"10.2106/jbjs.rvw.24.00106","title":"The Accuracy of Artificial Intelligence Models in Hand/Wrist Fracture and Dislocation Diagnosis","year":2024,"lang":"en","type":"review","venue":"JBJS Reviews","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Wrist; Confidence interval; Meta-analysis; MEDLINE; Systematic review; Radiography; Critical appraisal; Bivariate analysis; Physical therapy; Radiology; Machine learning; Internal medicine; Pathology","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":[0.09484246,0.002818796,0.01021481,0.01099235,0.0007013381,0.007943558,0.003389587,0.003476261,0.00233327],"category_scores_gemma":[0.2744367,0.001768726,0.0305861,0.006735148,0.001872512,0.004315073,0.00225073,0.002861889,0.0003241876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004000012,"about_ca_system_score_gemma":0.005403419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009723787,"about_ca_topic_score_gemma":0.009374762,"domain_scores_codex":[0.9000365,0.07200465,0.01437109,0.004230247,0.008774753,0.0005828324],"domain_scores_gemma":[0.6340922,0.3302346,0.02242218,0.004505379,0.008068387,0.0006772808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00403126,0.0002217108,0.05119512,0.3653072,0.395594,0.0002470741,0.0005775535,0.02186272,0.0002256146,0.002489883,0.002796188,0.1554517],"study_design_scores_gemma":[0.002524999,0.002609422,0.03048945,0.1847104,0.7090708,0.0007178352,0.0004829856,0.03893325,0.0007148368,0.01631624,0.013026,0.0004038751],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01235254,0.9739257,0.008098024,0.002108712,0.0004740569,0.0006791433,0.000779072,0.00007561906,0.001507089],"genre_scores_gemma":[0.5902497,0.3774684,0.02652216,0.001754972,0.0008023135,0.001567999,0.001255119,0.00005182316,0.0003274463],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.09484246,"threshold_uncertainty_score":0.5015808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3962541033487441,"score_gpt":0.5283794052264985,"score_spread":0.1321253018777544,"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."}}