{"id":"W4409460005","doi":"10.1007/s40477-025-01019-6","title":"Wrist and elbow fracture detection and segmentation by artificial intelligence using point-of-care ultrasound","year":2025,"lang":"en","type":"article","venue":"Journal of Ultrasound","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Alberta Machine Intelligence Institute; Alberta Innovates; Women and Children's Health Research Institute; Canadian Institute for Advanced Research; TD Bank","keywords":"Medicine; Ultrasound; Wrist; Elbow; Segmentation; Fracture (geology); Point of care ultrasound; Point of care; Artificial intelligence; Radiology; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003573552,0.0001194518,0.000271812,0.0002120259,0.0001496685,0.00005405174,0.00004553785,0.0001336016,0.00003461154],"category_scores_gemma":[0.0009211177,0.0001052438,0.00005869886,0.000247843,0.0001377324,0.0002349331,0.000007363487,0.0003007602,8.335309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422301,"about_ca_system_score_gemma":0.0001709472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002033066,"about_ca_topic_score_gemma":0.0000500591,"domain_scores_codex":[0.9987385,0.00005890224,0.0007113157,0.0001447075,0.0002067546,0.0001398749],"domain_scores_gemma":[0.998215,0.0005763219,0.0003958858,0.00009745875,0.000610573,0.0001047207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001183104,0.000239099,0.05092998,0.0006825571,0.0001794022,0.000008434857,0.009291839,0.0001486745,0.6452056,0.0001301595,0.0005314377,0.2914697],"study_design_scores_gemma":[0.0001066101,0.0008579995,0.008908144,0.0005256979,0.0003682169,0.0006674784,0.04209513,0.0001970812,0.9378266,0.007481745,0.000808039,0.000157293],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9510452,0.003336991,0.0442638,0.0004790267,0.0005936649,0.0002027674,0.0000050655,0.000006341785,0.00006721657],"genre_scores_gemma":[0.9964224,0.001046819,0.001944085,0.0002841887,0.0002623168,0.000001472094,0.000006525396,0.000009219583,0.00002297783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.292621,"threshold_uncertainty_score":0.4291718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04818323598874907,"score_gpt":0.3913099007885046,"score_spread":0.3431266647997555,"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."}}