{"id":"W4415604664","doi":"10.3389/fradi.2025.1670517","title":"A systematic review and meta-analysis of GPT-based differential diagnostic accuracy in radiological cases: 2023–2025","year":2025,"lang":"en","type":"review","venue":"Frontiers in Radiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Radiological weapon; Diagnostic accuracy; Differential (mechanical device); Patient data; Systematic error; MEDLINE","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001110711,0.0004491058,0.01455291,0.001837472,0.00003150295,0.000007446654,0.0002641548,0.0006568299,0.0002479889],"category_scores_gemma":[0.01785898,0.000299762,0.001617704,0.002025463,0.0002267666,0.0000285289,0.00004641299,0.0006407251,0.000003986398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003574016,"about_ca_system_score_gemma":0.0007108307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003088315,"about_ca_topic_score_gemma":0.0001134604,"domain_scores_codex":[0.9939165,0.002155049,0.002745959,0.0006623573,0.0001447883,0.0003754147],"domain_scores_gemma":[0.9873385,0.01094638,0.0008256324,0.0006899385,0.00008371108,0.0001158308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00002028118,0.0001507138,0.0004088643,0.9530113,0.03679739,0.0001108174,0.00006268921,0.000007216411,1.547725e-8,0.0000637483,0.002267938,0.007098978],"study_design_scores_gemma":[0.00006065283,0.0001847595,0.00003528098,0.07910956,0.9178248,0.00007950183,0.0001180339,0.0001660209,1.853384e-7,0.0001175009,0.00204584,0.0002578426],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002062135,0.992967,0.001482402,0.000420404,0.0005127388,0.004458609,0.0001025585,0.00001198498,0.00002368502],"genre_scores_gemma":[0.0003717238,0.996171,0.0003499695,0.0005596443,0.00003786207,0.001875047,0.0004835228,0.00001441656,0.0001368275],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8810275,"threshold_uncertainty_score":0.9999455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2129955385157616,"score_gpt":0.4678035737716635,"score_spread":0.254808035255902,"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."}}