{"id":"W4399305961","doi":"10.2196/preprints.60827","title":"The comparative sufficiency of ChatGPT, Google Bard, and Bing AI in answering diagnosis, treatment, and prognosis questions about common dermatological diagnoses (Preprint)","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SKiN Health","funders":"","keywords":"Preprint; Medical diagnosis; Medicine; Dermatology; Computer science; World Wide Web; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01762201,0.0004414446,0.000464644,0.002893967,0.0006690603,0.002867745,0.0006782031,0.001718709,0.008995783],"category_scores_gemma":[0.1787377,0.0004829759,0.0006047255,0.00104514,0.0009781049,0.003776864,0.001854474,0.001378385,0.003267984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000721051,"about_ca_system_score_gemma":0.001125874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003888549,"about_ca_topic_score_gemma":0.005143006,"domain_scores_codex":[0.9867633,0.008872971,0.001123537,0.00103572,0.001771257,0.0004332753],"domain_scores_gemma":[0.6221759,0.3485142,0.007126734,0.007446473,0.01094599,0.003790622],"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":[0.02455349,0.003164013,0.2482881,0.005673799,0.0009905369,0.0005885557,0.009986401,0.005859199,0.01347428,0.003743622,0.03482998,0.6488482],"study_design_scores_gemma":[0.002280953,0.01513566,0.779702,0.002835751,0.002173719,0.002762977,0.01603136,0.09008802,0.02465691,0.01150307,0.05229533,0.0005341753],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9442341,0.002499772,0.006943775,0.004245128,0.0004815164,0.0005240627,0.005544395,0.00234233,0.03318495],"genre_scores_gemma":[0.9776719,0.0008103564,0.00948573,0.0009875944,0.000234529,0.0003373873,0.004691797,0.0004294206,0.005351304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01762201,"threshold_uncertainty_score":0.0931952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1129791134848848,"score_gpt":0.4430767732128238,"score_spread":0.330097659727939,"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."}}