{"id":"W4409996631","doi":"10.1007/s00261-025-04910-2","title":"External validation of an RSNA 2023 Abdominal Trauma AI Challenge high performing machine learning model in the detection and grading of splenic injuries on CT","year":2025,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Abdominal Trauma and Injuries","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"North York General Hospital; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Hepatology; Grading (engineering); Internal medicine; Radiology; Medical physics","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":[0.01450938,0.001789689,0.001136861,0.00175581,0.0010659,0.002358279,0.002073094,0.003245879,0.002242189],"category_scores_gemma":[0.02470507,0.000398966,0.001387601,0.0006092518,0.001157583,0.001038333,0.002134124,0.001674262,0.003098645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008922666,"about_ca_system_score_gemma":0.001867309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006994148,"about_ca_topic_score_gemma":0.006792868,"domain_scores_codex":[0.9952558,0.00220819,0.0003533377,0.001152773,0.0007173381,0.0003125804],"domain_scores_gemma":[0.9845766,0.007815762,0.0005944929,0.002103502,0.004354394,0.0005550885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005806644,0.003061611,0.2165142,0.0009824402,0.002668086,0.001136507,0.0009021859,0.3454005,0.03999487,0.00194245,0.0338771,0.3477134],"study_design_scores_gemma":[0.0001956718,0.0009708905,0.02880954,0.0001801664,0.0004851696,0.0004869436,0.0002905231,0.9351298,0.02733608,0.001139728,0.004902206,0.00007329934],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9326233,0.00181509,0.0513398,0.0007924523,0.0007826912,0.0004151412,0.002745753,0.003342281,0.006143391],"genre_scores_gemma":[0.9746448,0.000137083,0.01604779,0.0003377548,0.00009208778,0.0001122214,0.006085717,0.000174602,0.002367992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01450938,"threshold_uncertainty_score":0.07673383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0183701034006153,"score_gpt":0.3029266788456622,"score_spread":0.2845565754450469,"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."}}