{"id":"W4399042780","doi":"10.3390/jpm14060568","title":"Evaluation of ChatGPT as a Counselling Tool for Italian-Speaking MASLD Patients: Assessment of Accuracy, Completeness and Comprehensibility","year":2024,"lang":"en","type":"article","venue":"Journal of Personalized Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Concordance; Completeness (order theory); Likert scale; Medicine; Referral; Affect (linguistics); Artificial intelligence; Natural language processing; Medical physics; Family medicine; Computer science; Psychology; Internal medicine; Mathematics; Developmental psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01386863,0.0006713188,0.0008700673,0.001667147,0.0005565186,0.001081847,0.000803884,0.0006322074,0.003717379],"category_scores_gemma":[0.04305047,0.0002139961,0.0009494944,0.0007972874,0.0005597034,0.000670663,0.001572999,0.0006485611,0.0008639778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009430602,"about_ca_system_score_gemma":0.00123952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001593655,"about_ca_topic_score_gemma":0.002810674,"domain_scores_codex":[0.993483,0.004059894,0.0006501309,0.0003795043,0.001118632,0.0003088582],"domain_scores_gemma":[0.9528461,0.03408799,0.00410032,0.001417137,0.005195882,0.00235267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004961379,0.001801295,0.6016751,0.002489426,0.0003626788,0.001462326,0.03335983,0.002052378,0.006792845,0.0002934204,0.007112231,0.3376372],"study_design_scores_gemma":[0.0004736072,0.006737564,0.9423994,0.0008857147,0.0005527867,0.003844256,0.0135575,0.01658363,0.006499706,0.0005039893,0.007713077,0.0002487892],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943601,0.0003111587,0.002029124,0.0002571778,0.00003456423,0.0004305763,0.0003862541,0.0002016911,0.00198912],"genre_scores_gemma":[0.9885433,0.000325618,0.008794854,0.0001286486,0.00003760992,0.0005808977,0.0005531128,0.00002842549,0.001007714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01386863,"threshold_uncertainty_score":0.07334518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2585734327725681,"score_gpt":0.5178133742795704,"score_spread":0.2592399415070024,"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."}}