{"id":"W3019166536","doi":"10.1007/s00256-020-03429-5","title":"Modernization of bone age assessment: comparing the accuracy and reliability of an artificial intelligence algorithm and shorthand bone age to Greulich and Pyle","year":2020,"lang":"en","type":"article","venue":"Skeletal Radiology","topic":"Forensic Anthropology and Bioarchaeology Studies","field":"Arts and Humanities","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Gold standard (test); Medicine; Bone age; Radiography; Intraclass correlation; Algorithm; Reliability (semiconductor); Standard deviation; Orthodontics; Nuclear medicine; Radiology; Statistics; Mathematics; Internal 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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000237733,0.0001180003,0.0004015486,0.00003832872,0.000237376,0.00001100804,0.00006514441,0.00006596246,0.00002896639],"category_scores_gemma":[0.0001294054,0.0000828647,0.00002337625,0.00003715272,0.01084528,0.00008437004,0.0001863434,0.000144399,4.608568e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000046812,"about_ca_system_score_gemma":0.00001219154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005258384,"about_ca_topic_score_gemma":0.002328307,"domain_scores_codex":[0.9990909,0.0001326483,0.0003065204,0.000259168,0.0000566912,0.0001540925],"domain_scores_gemma":[0.9994606,0.0002124244,0.0001020678,0.0001094111,0.00006117062,0.00005437539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004035195,0.0002139649,0.03100599,0.0002791695,0.0002726768,0.00008878396,0.1565475,0.0001552432,0.001323022,0.6966326,0.0001731827,0.1129043],"study_design_scores_gemma":[0.002358573,0.0174303,0.264116,0.0001726512,0.001107151,0.0005464082,0.2600143,0.1536299,0.006375386,0.283894,0.00816562,0.002189776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911694,0.000669493,0.003766733,0.003790481,0.0001031732,0.0002089175,0.00002807862,0.00001505922,0.0002486556],"genre_scores_gemma":[0.9981344,0.0002400163,0.001278924,0.0001838488,0.0001155854,0.000005958425,0.00002018435,0.000005736402,0.00001531063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4127386,"threshold_uncertainty_score":0.9918466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066716581042124,"score_gpt":0.3039501587815454,"score_spread":0.2532829929711241,"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."}}