{"id":"W4405279532","doi":"10.1002/oto2.70048","title":"Enhancing Multilingual Patient Education: ChatGPT's Accuracy and Readability for SSNHL Queries in English and Spanish","year":2024,"lang":"en","type":"article","venue":"OTO Open","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Children's Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Readability; Computer science; Information retrieval; Natural language processing; World Wide Web; Programming language","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":[0.004582306,0.0004835081,0.0005998914,0.0006617643,0.0002962312,0.001152814,0.0005139001,0.0003941997,0.004831684],"category_scores_gemma":[0.04625374,0.0001439816,0.0005884974,0.0003619158,0.0003518971,0.0008275976,0.00160729,0.0005657597,0.0009600482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005195658,"about_ca_system_score_gemma":0.00103749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002362145,"about_ca_topic_score_gemma":0.003450599,"domain_scores_codex":[0.9964323,0.001986286,0.0003357357,0.0002724662,0.0007151918,0.0002580307],"domain_scores_gemma":[0.9667317,0.02342303,0.002937343,0.0009977,0.004162074,0.001748198],"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":[0.004847533,0.004007039,0.4469737,0.002407167,0.0003172619,0.001711988,0.05178343,0.00189918,0.01427249,0.0001409198,0.008275031,0.4633642],"study_design_scores_gemma":[0.0005693352,0.009585134,0.9245355,0.0007626205,0.0005400721,0.002985915,0.03054723,0.005853988,0.009710373,0.000352092,0.01431504,0.0002427973],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952357,0.0001560631,0.001097333,0.0002015169,0.00002448793,0.0001374623,0.0001708033,0.0001612253,0.002815306],"genre_scores_gemma":[0.9957028,0.0002142948,0.002502288,0.000128876,0.00002583132,0.0002109332,0.0001814481,0.00003823623,0.0009952384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004831684,"threshold_uncertainty_score":0.02423382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09553729462105923,"score_gpt":0.4576708846723533,"score_spread":0.3621335900512941,"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."}}