{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01228641,0.0004609491,0.0005362059,0.004046378,0.0005693058,0.002401209,0.001057857,0.001024316,0.001906021],"category_scores_gemma":[0.06138853,0.0002893299,0.000646907,0.001369644,0.001543871,0.001764389,0.001364204,0.001179731,0.0006235056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008223531,"about_ca_system_score_gemma":0.000849136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005664174,"about_ca_topic_score_gemma":0.006436886,"domain_scores_codex":[0.9959121,0.002046181,0.0003273804,0.0007575277,0.0008792811,0.00007758315],"domain_scores_gemma":[0.9601973,0.03042104,0.001196704,0.002166531,0.005752097,0.0002664029],"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":[0.001416969,0.0001774937,0.3649749,0.0003067457,0.0008118443,0.0001547649,0.001697312,0.03887487,0.004816461,0.009161042,0.001765752,0.5758418],"study_design_scores_gemma":[0.0001274156,0.001594723,0.3563868,0.0005382558,0.0008638901,0.002139024,0.001679283,0.5685543,0.02375234,0.03102649,0.01307614,0.0002613447],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8545076,0.005947417,0.1239611,0.002247229,0.0003662696,0.000130819,0.0004850918,0.0004169826,0.01193737],"genre_scores_gemma":[0.9471065,0.0009022277,0.05007406,0.0002110212,0.00007633887,0.00002462526,0.0001778105,0.0000611162,0.001366245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01228641,"threshold_uncertainty_score":0.06497753,"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."}}