{"id":"W3163526662","doi":"10.1111/ocr.12491","title":"Facial morphology analysis in osteogenesis imperfecta types I, III and IV using computer vision","year":2021,"lang":"en","type":"article","venue":"Orthodontics and Craniofacial Research","topic":"Connective tissue disorders research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Shriners Hospitals for Children - Canada; McGill University","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Dental and Craniofacial Research; Rare Diseases Clinical Research Network","keywords":"Craniofacial; Morphological analysis; Osteogenesis imperfecta; Landmark; Medicine; Artificial intelligence; Orthodontics; Computer science; Anatomy","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":[],"consensus_categories":[],"category_scores_codex":[0.001017402,0.0001401144,0.0002914495,0.0003251689,0.0002299107,0.0001064221,0.0001201107,0.00021104,0.00009744252],"category_scores_gemma":[0.0002995708,0.0001457693,0.00007971905,0.0008430688,0.0002562089,0.000007700641,0.0005695566,0.0002358376,0.000002527004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002292325,"about_ca_system_score_gemma":0.0001684897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006092142,"about_ca_topic_score_gemma":0.00256704,"domain_scores_codex":[0.9978679,0.0005254736,0.000199605,0.000613133,0.0003229781,0.0004708559],"domain_scores_gemma":[0.9990907,0.00009295729,0.00002551475,0.0002681087,0.0003866748,0.000135987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000284453,0.0001038276,0.3730127,0.00003364126,0.0002199688,0.0001435706,0.0002110609,0.0001007404,0.585961,0.0001763797,0.00005891063,0.03969373],"study_design_scores_gemma":[0.004605178,0.001572503,0.9124017,0.00004909118,0.0002664159,0.000175054,0.001368713,0.02667783,0.03993171,0.0004205394,0.0114928,0.001038455],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952979,0.001461372,0.002596586,0.0001832003,0.00004445658,0.0001791861,0.00002308098,0.000003663071,0.0002105251],"genre_scores_gemma":[0.9973296,0.0012525,0.0009302,0.00003295753,0.0001028138,0.000008382121,0.00006071847,0.00001830979,0.0002645034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5460293,"threshold_uncertainty_score":0.5944301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04497674325167805,"score_gpt":0.3855423415550365,"score_spread":0.3405655983033585,"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."}}