{"id":"W4400772352","doi":"10.2196/59273","title":"Claude 3 Opus and ChatGPT With GPT-4 in Dermoscopic Image Analysis for Melanoma Diagnosis: Comparative Performance Analysis","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medical diagnosis; McNemar's test; Medicine; Preprint; Dermatology; Artificial intelligence; Computer science; Pathology; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003117492,0.0002006127,0.0006608774,0.001055293,0.00006553091,0.00009770052,0.00009646017,0.000122683,0.000291984],"category_scores_gemma":[0.00002671381,0.0001423789,0.0001547385,0.002086801,0.0001337981,0.0002022061,0.00005573804,0.0002873018,0.00002458492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001007279,"about_ca_system_score_gemma":0.00009116587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002579494,"about_ca_topic_score_gemma":0.0003257244,"domain_scores_codex":[0.9983653,0.00002242029,0.0005915337,0.000188371,0.0005427732,0.0002896393],"domain_scores_gemma":[0.9991631,0.0001693989,0.00008964558,0.0002377437,0.00006677047,0.0002733355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002133781,0.001710829,0.6637838,0.01574731,0.05125407,0.001603671,0.09299428,0.001303415,0.00008583799,0.001912976,0.01281464,0.1546554],"study_design_scores_gemma":[0.002519002,0.001300777,0.09349795,0.0006055573,0.007021805,0.0001721863,0.005978061,0.8624299,0.0004094669,0.00002358871,0.02563308,0.000408693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9790446,0.0003609028,0.01692225,0.0006806122,0.00007554898,0.0009332774,0.00001553266,0.0001148815,0.001852369],"genre_scores_gemma":[0.9948514,0.0003107784,0.003083338,0.0006461544,0.00005822726,0.0005478741,0.00009729794,0.0000113699,0.0003936171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8611264,"threshold_uncertainty_score":0.5806041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01533862173358607,"score_gpt":0.307656231627764,"score_spread":0.2923176098941779,"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."}}