{"id":"W4409657910","doi":"10.1097/rct.0000000000001709","title":"Beyond Human Limits: The Promise and Pitfalls of Large Language Models in Radiology Research","year":2025,"lang":"en","type":"review","venue":"Journal of Computer Assisted Tomography","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Medicine; Productivity; Engineering ethics; Data science; Computer science","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":[0.02941651,0.00104066,0.002487015,0.003186199,0.0005786764,0.005179293,0.002651682,0.003469556,0.003177992],"category_scores_gemma":[0.07095835,0.0008482137,0.001863981,0.002774205,0.003553179,0.008996935,0.002712092,0.005920463,0.001862076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00203683,"about_ca_system_score_gemma":0.007717844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003634973,"about_ca_topic_score_gemma":0.004970327,"domain_scores_codex":[0.9846001,0.01121998,0.001028481,0.0006401375,0.002347616,0.0001637661],"domain_scores_gemma":[0.8358165,0.1556236,0.001895059,0.002589182,0.003525218,0.0005503551],"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":[0.00007842433,0.0000445763,0.0004282675,0.02244761,0.0003772888,0.0001333135,0.0005778081,0.002796237,0.0002799117,0.05992263,0.01524791,0.897666],"study_design_scores_gemma":[0.00009295881,0.0002504143,0.001017888,0.04958206,0.0007720758,0.001011225,0.0005919375,0.004127195,0.0008566597,0.1741399,0.7673834,0.0001741961],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002426831,0.9788215,0.009106949,0.009163731,0.0003341704,0.000030131,0.00004388566,0.00006183383,0.00219515],"genre_scores_gemma":[0.00916607,0.9689744,0.01466957,0.005463212,0.0008591929,0.0002122085,0.00008278754,0.0000498857,0.0005227356],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.02941651,"threshold_uncertainty_score":0.1555713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2145296303470314,"score_gpt":0.504344560250096,"score_spread":0.2898149299030646,"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."}}