{"id":"W4411801306","doi":"10.3390/info16070549","title":"Large Language Models in Medical Chatbots: Opportunities, Challenges, and the Need to Address AI Risks","year":2025,"lang":"en","type":"article","venue":"Information","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Data science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009025427,0.0000612979,0.0001253082,0.0001961991,0.00005783843,0.00002098281,0.00006178541,0.0001043223,0.00004713899],"category_scores_gemma":[0.0003863292,0.00004363155,0.0000170125,0.0001288813,0.00003813405,0.0003992292,0.00003551016,0.0001882316,0.00002153376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005648951,"about_ca_system_score_gemma":0.0002314314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001308215,"about_ca_topic_score_gemma":0.0005971604,"domain_scores_codex":[0.9991831,0.00004493794,0.0003563185,0.00005864462,0.0002067211,0.0001502349],"domain_scores_gemma":[0.9995065,0.0001164911,0.00004168478,0.0001469592,0.00009606604,0.00009225192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003017839,0.00004154491,0.0001978331,0.0002200963,0.00001172375,0.000003600797,0.1165107,0.00003828245,0.000001176098,0.1005139,0.002474796,0.7796846],"study_design_scores_gemma":[0.002677362,0.0002542095,0.01278743,0.002224476,0.00007950584,0.00005680339,0.5558245,0.2254599,0.0006452553,0.02603714,0.1735549,0.0003984595],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5077003,0.007037713,0.01126737,0.3948441,0.0008940528,0.002177728,0.00001969509,0.000122992,0.07593607],"genre_scores_gemma":[0.9786007,0.00251792,0.00002319274,0.01851727,0.00007156029,0.00009131206,0.00005225525,0.000002610881,0.0001232057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7792861,"threshold_uncertainty_score":0.1977638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2297562887951659,"score_gpt":0.4405707767466559,"score_spread":0.21081448795149,"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."}}