{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004562106,0.0003992305,0.01124877,0.0004797584,0.00005933022,0.0000201962,0.0001072942,0.000155987,0.00004205725],"category_scores_gemma":[0.003244556,0.0002378207,0.0006002715,0.001284965,0.0002472624,0.0001163589,0.00004722008,0.0003281568,0.000006429147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006036049,"about_ca_system_score_gemma":0.0001903917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005910867,"about_ca_topic_score_gemma":0.000007266336,"domain_scores_codex":[0.9969245,0.0001483965,0.00197579,0.0004153145,0.000338181,0.0001978747],"domain_scores_gemma":[0.9945521,0.003709665,0.0008229995,0.0004617083,0.0003073453,0.0001462158],"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":[0.000001123857,0.00003405871,0.0000751193,0.7599484,0.0409257,0.00000138896,0.0003306386,1.905343e-7,9.900789e-9,0.00001893385,0.0003821173,0.1982823],"study_design_scores_gemma":[0.00001693639,0.0002594722,0.000009980699,0.2269601,0.7678839,0.000006474462,0.0001444481,0.00003072021,9.110726e-7,0.00001315557,0.004542395,0.0001314914],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003325475,0.9948751,0.0001339598,0.001608922,0.00005186108,0.002794931,0.0001351569,0.00001756075,0.0003492772],"genre_scores_gemma":[0.005033895,0.992389,0.0000167426,0.0009852183,0.0001170375,0.0003428877,0.0005350723,0.00001802299,0.0005621049],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7269582,"threshold_uncertainty_score":0.9698046,"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."}}