{"id":"W4406102349","doi":"10.1016/j.acra.2024.11.053","title":"Leveraging Large Language Models in Radiology Research: A Comprehensive User Guide","year":2025,"lang":"en","type":"review","venue":"Academic Radiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Process (computing); Alliance; Task (project management); Computer science; Medicine; Radiology; Political science; Engineering","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":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.002273189,0.0003921393,0.002461781,0.003084357,0.000132454,0.000006603956,0.0005085382,0.002215597,0.0001347337],"category_scores_gemma":[0.001846219,0.0003373808,0.0002743163,0.001931499,0.0002786656,0.0000801773,0.0002022916,0.005152753,0.0002178309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008229866,"about_ca_system_score_gemma":0.002057851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001177682,"about_ca_topic_score_gemma":0.00006483644,"domain_scores_codex":[0.9940904,0.002018894,0.00160821,0.0008810776,0.0002184426,0.001182995],"domain_scores_gemma":[0.9946346,0.004001899,0.0002523338,0.0006873157,0.0002276034,0.0001962491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005150928,0.00005785584,0.0004203699,0.01273514,0.0001506599,0.0002663823,0.005127523,0.00002040188,0.000008249084,0.004435512,0.08374394,0.8929825],"study_design_scores_gemma":[0.00009517024,0.00009582262,0.00001658561,0.008374904,0.0001536237,0.0009059476,0.002341634,0.000125544,0.000003696504,0.001987287,0.9856729,0.0002269187],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001259518,0.9912933,0.0001434163,0.001623546,0.0008429382,0.001758716,0.00001914257,0.00006475997,0.002994693],"genre_scores_gemma":[0.000296291,0.9921478,0.0002296546,0.001779625,0.001111217,0.0004196587,0.0004234038,0.00004933406,0.003543037],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9019289,"threshold_uncertainty_score":0.9999079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4934163673463529,"score_gpt":0.5746904848411112,"score_spread":0.08127411749475832,"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."}}