{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008498974,0.0009560429,0.00101104,0.002799122,0.0003302569,0.001255622,0.0008710464,0.001271456,0.001348256],"category_scores_gemma":[0.02346848,0.0003377274,0.001107911,0.0009624886,0.0005143706,0.0009927886,0.001289657,0.0006897729,0.0006010681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038217,"about_ca_system_score_gemma":0.0009979769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006233409,"about_ca_topic_score_gemma":0.005082021,"domain_scores_codex":[0.9965706,0.00179895,0.0002416815,0.0005655747,0.0006219916,0.0002012517],"domain_scores_gemma":[0.9832762,0.01310289,0.0005424641,0.0007328355,0.001795377,0.0005502137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02487703,0.001276405,0.2497133,0.001524044,0.002813881,0.001036978,0.0007471188,0.1395399,0.01613897,0.001304268,0.009335134,0.551693],"study_design_scores_gemma":[0.0002705391,0.003858207,0.06470001,0.00009666534,0.0006901193,0.001564289,0.0003256276,0.9111544,0.01402825,0.001047906,0.002160706,0.0001032501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9648046,0.004417408,0.02430068,0.000408527,0.000150576,0.0002909262,0.001004191,0.002298497,0.002324542],"genre_scores_gemma":[0.969994,0.0005423131,0.02720514,0.0000742982,0.00005720197,0.0001208143,0.001205966,0.00009962728,0.0007006337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008498974,"threshold_uncertainty_score":0.04494745,"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."}}