{"id":"W4408736524","doi":"10.1038/s41746-025-01543-z","title":"A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians","year":2025,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Meta-analysis; Generative grammar; Reliability (semiconductor); Diagnostic accuracy; Systematic review; Artificial intelligence; Diagnostic test; Computer science; Medical physics; MEDLINE; Machine learning; Medicine; Pathology; Internal medicine; Pediatrics","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":[0.01540642,0.002167329,0.01002538,0.006497848,0.0006557204,0.002940767,0.002152815,0.001736272,0.004894048],"category_scores_gemma":[0.07702139,0.001059922,0.02156795,0.006806619,0.0007776038,0.001977684,0.001459118,0.001683062,0.000435434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003127815,"about_ca_system_score_gemma":0.005321435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007525532,"about_ca_topic_score_gemma":0.01825865,"domain_scores_codex":[0.9882549,0.005337525,0.003625771,0.00106959,0.001484944,0.0002271925],"domain_scores_gemma":[0.9437883,0.04804485,0.004450383,0.0009181117,0.00252238,0.0002760015],"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":[0.001051432,0.00002634349,0.002915172,0.817026,0.1306781,0.00009432112,0.0001341306,0.0004336009,0.0001623809,0.0002916747,0.001687503,0.04549929],"study_design_scores_gemma":[0.0006893171,0.0003383664,0.006457627,0.2767493,0.7035151,0.0002893263,0.0001099106,0.0002570748,0.0002934756,0.0007718186,0.01047766,0.00005099583],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001328404,0.9970558,0.0003853871,0.0001803844,0.00009326742,0.0002055282,0.0004629552,0.00001333474,0.0002750127],"genre_scores_gemma":[0.04304292,0.9525092,0.001776225,0.0007274768,0.000161832,0.0007467781,0.0008466803,0.00002108295,0.0001678546],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01540642,"threshold_uncertainty_score":0.08147788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2951728046467549,"score_gpt":0.5007602912495945,"score_spread":0.2055874866028396,"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."}}