{"id":"W4414120402","doi":"10.1016/j.jacr.2025.09.004","title":"Leveraging Large Language Models to Enhance Radiology Report Readability: A Systematic Review","year":2025,"lang":"en","type":"review","venue":"Journal of the American College of Radiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Set (abstract data type); Best practice; MEDLINE; Systematic review; English language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01006854,0.001581507,0.008201467,0.003415201,0.0003272073,0.002310957,0.001955915,0.001542803,0.004168362],"category_scores_gemma":[0.04648962,0.0009227202,0.009317343,0.00338308,0.0007862906,0.003350358,0.001256051,0.001777649,0.0004871527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001235393,"about_ca_system_score_gemma":0.004557807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006330398,"about_ca_topic_score_gemma":0.02403535,"domain_scores_codex":[0.9940913,0.002946274,0.001464311,0.0005583604,0.0008347773,0.0001049472],"domain_scores_gemma":[0.9663046,0.02840276,0.00341734,0.0004890474,0.001238408,0.00014789],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.001565172,0.000188915,0.004231994,0.7535506,0.05811873,0.0001206294,0.0004369852,0.0007804864,0.0003916897,0.000351877,0.003699269,0.1765638],"study_design_scores_gemma":[0.003147676,0.001622324,0.01735257,0.4295742,0.5181135,0.0004467616,0.0006206301,0.001968375,0.0006747285,0.002146444,0.02407531,0.0002574742],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004737758,0.9924117,0.0009876401,0.0003734089,0.0001124868,0.0004445746,0.0006267615,0.00003952995,0.0002661267],"genre_scores_gemma":[0.08734445,0.904022,0.005028603,0.001276573,0.000177982,0.0009619353,0.0008556895,0.00003817472,0.000294657],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9899315,"threshold_uncertainty_score":0.05324817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08771838626067138,"score_gpt":0.4538041268876007,"score_spread":0.3660857406269293,"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."}}