{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002305842,0.0001772925,0.0007586078,0.001130852,0.0001272549,0.00001981795,0.0001450085,0.0002728904,0.0001117507],"category_scores_gemma":[0.0001455359,0.0001758874,0.0001399074,0.002211157,0.0001928046,0.0001257281,0.00005007389,0.0004033323,0.000120332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001451657,"about_ca_system_score_gemma":0.0005145183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003752168,"about_ca_topic_score_gemma":0.0008951662,"domain_scores_codex":[0.9977209,0.0002732777,0.0009904413,0.0004246663,0.0001591059,0.0004315871],"domain_scores_gemma":[0.9986637,0.0004770677,0.0001365226,0.0003628376,0.0002647687,0.00009511741],"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":[0.001549294,0.002184572,0.4873138,0.0009339927,0.001462982,0.0005237692,0.03378323,0.03314735,0.001903539,0.2362678,0.00300844,0.1979212],"study_design_scores_gemma":[0.00008213403,0.00009974006,0.01376199,0.0001483565,0.0005215339,0.0002912285,0.01021754,0.7988214,0.03583552,0.1395953,0.0003386904,0.0002864921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.954976,0.0005341637,0.0264465,0.01195871,0.0003118745,0.0007719041,0.000002004659,0.00007287427,0.004925944],"genre_scores_gemma":[0.9966053,0.00003310146,0.001560264,0.001342273,0.00003594103,0.0002687689,0.00004289726,0.000006093977,0.0001053862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7656741,"threshold_uncertainty_score":0.7172478,"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."}}