{"id":"W4388078979","doi":"10.2196/49280","title":"Evaluation of ChatGPT Dermatology Responses to Common Patient Queries","year":2023,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Dermatology; Medicine; Computer science; Information retrieval","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":[0.0003859508,0.0001056084,0.0003426026,0.0004278974,0.00008347515,0.000004697365,0.00007137185,0.0001707364,0.0001409829],"category_scores_gemma":[0.0007753295,0.0001006033,0.00005262149,0.0005433606,0.0001097371,0.00005265234,0.00004504536,0.0001182002,0.000539784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008188253,"about_ca_system_score_gemma":0.0004179588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001798055,"about_ca_topic_score_gemma":0.0001796682,"domain_scores_codex":[0.9981294,0.0004318065,0.0005554797,0.0002056077,0.0003840699,0.0002936687],"domain_scores_gemma":[0.9984748,0.0003290995,0.0001228862,0.0003210622,0.0006300583,0.0001220793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00143709,0.0005196687,0.5161129,0.0006705806,0.0001321714,0.0002338878,0.04065641,0.00009934461,0.009172138,0.003232694,0.05329707,0.3744361],"study_design_scores_gemma":[0.000505844,0.001294702,0.344143,0.0003760965,0.0003447435,0.004433374,0.02211509,0.008027661,0.5444428,0.01289388,0.06089268,0.0005300731],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736803,0.000194937,0.00003002082,0.02382467,0.0005244503,0.0009312018,0.000005351667,0.0001011837,0.0007079139],"genre_scores_gemma":[0.9980848,0.0000352679,0.0001022681,0.001169592,0.00004453957,0.0004395602,0.00004656553,0.0000146166,0.00006280091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5352707,"threshold_uncertainty_score":0.6938011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2224496072839383,"score_gpt":0.4953655900003545,"score_spread":0.2729159827164163,"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."}}