{"id":"W4393082517","doi":"10.2196/55595","title":"Exploring the Performance of ChatGPT-4 in the Taiwan Audiologist Qualification Examination: Preliminary Observational Study Highlighting the Potential of AI Chatbots in Hearing Care","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Audiologist; Audiology; Psychology; Rehabilitation; Health care; Medicine; Hearing loss; Neuroscience","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":[0.002466383,0.00009896719,0.0001579626,0.000175298,0.0001321937,0.00002277395,0.0002447854,0.00007410755,0.00003382639],"category_scores_gemma":[0.0007257142,0.00005493943,0.00004306652,0.0008042481,0.0001501608,0.0002174586,0.00003104277,0.0004993384,0.000004659746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000161295,"about_ca_system_score_gemma":0.001261718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008103566,"about_ca_topic_score_gemma":0.0001693966,"domain_scores_codex":[0.9978388,0.0003667324,0.0007234593,0.000220266,0.0006900905,0.0001606841],"domain_scores_gemma":[0.9988503,0.0004326624,0.0001309632,0.0003121004,0.0002339289,0.0000400365],"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":[0.0001388572,0.001245387,0.2603588,0.001104473,0.00001997574,0.000003878809,0.3151391,0.0002473985,0.0003479816,0.002781815,0.0002682443,0.4183441],"study_design_scores_gemma":[0.00004924191,0.0003212302,0.8434591,0.0006656303,0.00001969242,0.00001223251,0.149165,0.005508939,0.0004477111,0.00007431459,0.0002286229,0.00004827091],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9580245,0.0007574617,0.00003369424,0.03892588,0.000948969,0.00120736,8.058414e-7,0.00001492639,0.00008642543],"genre_scores_gemma":[0.9976234,0.0001516842,0.00002495806,0.0003984365,0.0006473836,0.001061949,0.00005569693,0.000009473862,0.00002697284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5831003,"threshold_uncertainty_score":0.2240365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2756492139671869,"score_gpt":0.4586515506990061,"score_spread":0.1830023367318192,"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."}}