{"id":"W4415778087","doi":"10.2196/74040","title":"Evaluating Artificial Intelligence Models in Dermatology: Comparative Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"CLARITY; Applications of artificial intelligence; Key (lock); Measure (data warehouse); Interpretability","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":[0.05144953,0.001014595,0.001504016,0.006140143,0.0005896051,0.004263189,0.001651991,0.001592812,0.006100215],"category_scores_gemma":[0.2604547,0.00025714,0.002755437,0.005132165,0.001154061,0.002949888,0.002063232,0.00151594,0.000888396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003023105,"about_ca_system_score_gemma":0.001711083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003347928,"about_ca_topic_score_gemma":0.004176021,"domain_scores_codex":[0.9563978,0.03492188,0.002918159,0.001173392,0.004274065,0.000314773],"domain_scores_gemma":[0.4674608,0.5044366,0.01027956,0.007585509,0.009072793,0.001164802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02523062,0.003248595,0.1771184,0.03109035,0.01769109,0.0004679545,0.002031888,0.08681666,0.001309498,0.008173149,0.02166176,0.6251601],"study_design_scores_gemma":[0.006887753,0.02506293,0.2159131,0.02291448,0.0372773,0.002781025,0.005212901,0.5328147,0.007538244,0.08473331,0.05811565,0.000748667],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6898857,0.2071192,0.05343812,0.01160964,0.00145049,0.003106165,0.008801362,0.0008530572,0.02373618],"genre_scores_gemma":[0.9582469,0.01533498,0.02046083,0.0008284843,0.0004725577,0.0005685413,0.003209614,0.00008999894,0.0007880647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05144953,"threshold_uncertainty_score":0.2720944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3828971437959041,"score_gpt":0.5537143426816791,"score_spread":0.170817198885775,"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."}}