{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001020282,0.0002239962,0.0006274356,0.0004675612,0.0001465511,0.00001056073,0.0001540291,0.0001205286,0.00002563696],"category_scores_gemma":[0.0001983044,0.0001701089,0.0001050093,0.0002055139,0.0003347374,0.0001896483,0.00003405509,0.000590608,0.000001357099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006397563,"about_ca_system_score_gemma":0.00005902113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003100242,"about_ca_topic_score_gemma":0.0001140332,"domain_scores_codex":[0.9982784,0.0003129849,0.0005996011,0.0003289789,0.0002078525,0.0002721436],"domain_scores_gemma":[0.9990269,0.000393845,0.0002308382,0.0002348776,0.00006398234,0.00004954285],"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":[0.02014531,0.0007341699,0.01693991,0.0009715246,0.0002348194,0.0001034859,0.00777734,0.002044203,0.1493145,0.01188203,0.00001830442,0.7898344],"study_design_scores_gemma":[0.01044361,0.01730761,0.156248,0.001398417,0.0009483425,0.001534699,0.009191451,0.2653397,0.516059,0.02064946,0.0002230244,0.0006566765],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943715,0.0007301983,0.003275847,0.0005204652,0.0001104483,0.000321345,0.000006301632,0.00001455928,0.0006492886],"genre_scores_gemma":[0.998333,0.0002749589,0.001019427,0.0001304371,0.00009364656,0.00003183201,0.0000127084,0.000015801,0.00008819105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7891778,"threshold_uncertainty_score":0.6936839,"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."}}