{"id":"W4408692716","doi":"10.2196/67299","title":"Assessing the Diagnostic Accuracy of ChatGPT-4 in Identifying Diverse Skin Lesions Against Squamous and Basal Cell Carcinoma","year":2025,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Basal cell carcinoma; Basal cell; Diagnostic accuracy; Dermatoscopy; Basal (medicine); Pathology; Dermatology; Skin cancer; Medicine; Cancer research; Internal medicine; Cancer; Melanoma","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005112373,0.0005067154,0.000372591,0.003332039,0.0005254396,0.00131133,0.0008724502,0.0008815575,0.00219239],"category_scores_gemma":[0.01557725,0.0001942476,0.0005155351,0.000820602,0.0008067111,0.0009792239,0.0009686627,0.000474628,0.0004960948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005573423,"about_ca_system_score_gemma":0.0005057843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002147715,"about_ca_topic_score_gemma":0.002947897,"domain_scores_codex":[0.9979954,0.0006934141,0.0002687686,0.0002331539,0.0005564576,0.0002528872],"domain_scores_gemma":[0.9925242,0.003564846,0.001135165,0.0003804338,0.001922791,0.0004725483],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007179483,0.00007292888,0.9803553,0.00009097411,0.0000659688,0.0002991989,0.0000926275,0.0002521758,0.00284372,0.00004883315,0.000154358,0.01500589],"study_design_scores_gemma":[0.00003625478,0.001274746,0.9707441,0.000203811,0.0003484998,0.00788228,0.001151612,0.007529448,0.008558113,0.0002947486,0.001944896,0.00003147008],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934835,0.001670918,0.001101268,0.0001268984,0.00004596885,0.00008474178,0.0002182775,0.00002963837,0.003238784],"genre_scores_gemma":[0.9975751,0.0002499642,0.001710971,0.00004447268,0.00003158368,0.0000192859,0.0001851665,0.000005603692,0.0001777617],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9948877,"threshold_uncertainty_score":0.02703714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02050781727261161,"score_gpt":0.32019733300373,"score_spread":0.2996895157311185,"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."}}