{"id":"W7111391779","doi":"10.3389/fradi.2025.1670517.s002","title":"Table 2_A systematic review and meta-analysis of GPT-based differential diagnostic accuracy in radiological cases: 2023–2025.docx","year":2025,"lang":"","type":"dataset","venue":"Figshare","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Diagnostic accuracy; Interquartile range; Radiological weapon; Differential diagnosis; Diagnostic odds ratio; Accuracy and precision; Patient data; Odds ratio","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008204574,0.003187055,0.009303655,0.01496402,0.0008479612,0.002981934,0.002416833,0.001647123,0.134493],"category_scores_gemma":[0.06063375,0.001267375,0.01610905,0.01378192,0.0005509022,0.004514154,0.001864879,0.001518794,0.006030815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002939722,"about_ca_system_score_gemma":0.006853972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007483449,"about_ca_topic_score_gemma":0.02307243,"domain_scores_codex":[0.9947361,0.001352299,0.002107939,0.000507048,0.0009831226,0.0003134797],"domain_scores_gemma":[0.957728,0.03221975,0.005624942,0.0007698272,0.00338701,0.0002705919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006086247,0.00001209914,0.001585142,0.9441171,0.01782976,0.0001154297,0.00007898066,0.0002233707,0.0002180744,0.0004783965,0.02603317,0.008699816],"study_design_scores_gemma":[0.004125232,0.0003569034,0.02277349,0.6815448,0.1746297,0.0007052333,0.0003497363,0.0009619533,0.0008495266,0.003654017,0.1098799,0.0001695927],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006259284,0.3471992,0.005575337,0.004668771,0.002563569,0.01532127,0.611916,0.00123268,0.005263899],"genre_scores_gemma":[0.1127263,0.4455828,0.03575096,0.01706097,0.002710661,0.1342034,0.2266542,0.001404244,0.02390647],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.865507,"threshold_uncertainty_score":0.4499238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112853755295549,"score_gpt":0.3500647106917228,"score_spread":0.2372109553961738,"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."}}