{"id":"W4320035860","doi":"10.2196/45529","title":"Analyzing the Predictability of an Artificial Intelligence App (Tibot) in the Diagnosis of Dermatological Conditions: A Cross-sectional Study","year":2023,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medical diagnosis; Categorical variable; Medicine; Artificial intelligence; Dermatology; Machine learning; Computer science; Pathology","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":[0.0005563447,0.0001070971,0.0003107289,0.0002286455,0.0001145856,0.00001650851,0.0002272148,0.00009706933,0.0001646283],"category_scores_gemma":[0.000274039,0.00006534291,0.00009949656,0.0007733813,0.0003984836,0.00004762683,0.00008131789,0.0002376304,0.00002435359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000278661,"about_ca_system_score_gemma":0.00003637942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006579895,"about_ca_topic_score_gemma":0.0002821332,"domain_scores_codex":[0.9982029,0.0004094207,0.0007019533,0.0002441395,0.0002465861,0.000194978],"domain_scores_gemma":[0.9986666,0.0006527731,0.0001526706,0.0003975854,0.00009324832,0.00003714504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001712946,0.001204281,0.9941029,0.00008220512,0.0000572897,0.0002802824,0.001562361,0.0001238804,0.0001277132,0.001493767,0.0001585868,0.0006354196],"study_design_scores_gemma":[0.0002462621,0.0002784924,0.9871336,0.00001165786,0.0000389785,0.001278655,0.005873853,0.002082128,0.0009958255,0.001869532,0.0001330832,0.00005792449],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970152,0.00002598541,0.0001502031,0.001069836,0.0001364928,0.00133427,0.00001747831,0.00006810088,0.0001824156],"genre_scores_gemma":[0.9991599,0.00001349211,0.00001689793,0.00012497,0.00002959129,0.0006119744,0.00002797428,0.000006224617,0.000009013585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006969311,"threshold_uncertainty_score":0.2664607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06325070408412378,"score_gpt":0.3829829749008234,"score_spread":0.3197322708166996,"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."}}