{"id":"W7106477366","doi":"","title":"Exploring and Comparing the Use of Large Language Models in Supporting Osteoporosis Health Consultations","year":2025,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Osteoporosis Canada","funders":"","keywords":"Bonferroni correction; Test (biology); Public health; Post-hoc analysis; Likert scale; Medical school; MEDLINE","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":[0.02257357,0.001543978,0.0009032776,0.002903776,0.0007683808,0.003590413,0.001433123,0.001900035,0.00181363],"category_scores_gemma":[0.1365033,0.0006582371,0.001467041,0.001498916,0.0006393294,0.005071299,0.002526595,0.001978418,0.0008716488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002626869,"about_ca_system_score_gemma":0.002255539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01255666,"about_ca_topic_score_gemma":0.01326058,"domain_scores_codex":[0.9739528,0.02177515,0.001177943,0.001475621,0.001236295,0.0003821178],"domain_scores_gemma":[0.6955338,0.2915933,0.003589993,0.003570606,0.004516313,0.001195966],"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":[0.01299578,0.007301554,0.2149049,0.003972526,0.002386465,0.0009604332,0.01866347,0.138694,0.01182754,0.004079306,0.007856085,0.5763578],"study_design_scores_gemma":[0.0005817256,0.002752595,0.02808545,0.0003907836,0.0009265444,0.0002354342,0.005259012,0.9483473,0.00441076,0.005540097,0.003199288,0.000270918],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.955709,0.001345145,0.03439122,0.001446471,0.0001186311,0.0007545682,0.001550771,0.001685191,0.002998916],"genre_scores_gemma":[0.9587806,0.0003302067,0.03708477,0.0002998797,0.00003851937,0.0004573721,0.002454526,0.00009494574,0.0004592634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02257357,"threshold_uncertainty_score":0.1193819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7753127538012896,"score_gpt":0.6539288468004174,"score_spread":0.1213839070008722,"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."}}