{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02394812,0.000971267,0.001146241,0.001755546,0.001323222,0.00765971,0.003767264,0.002892975,0.006939743],"category_scores_gemma":[0.06647654,0.0009649856,0.001847629,0.001130742,0.004881979,0.01592941,0.006217971,0.004954218,0.003658099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003267212,"about_ca_system_score_gemma":0.004927282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003691509,"about_ca_topic_score_gemma":0.004717845,"domain_scores_codex":[0.9826003,0.01171773,0.0009628191,0.001347653,0.002855474,0.0005159865],"domain_scores_gemma":[0.9319694,0.05399886,0.002414995,0.005602739,0.004531177,0.001482794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006850433,0.0003075925,0.007434919,0.00621746,0.0003689537,0.0009452657,0.009707674,0.05218862,0.0133426,0.4032979,0.03500997,0.4704941],"study_design_scores_gemma":[0.0001788145,0.0004710421,0.002103221,0.003535779,0.0003221128,0.001192778,0.003196635,0.2024061,0.009880699,0.4782386,0.2982031,0.0002711724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.02923494,0.01912197,0.8916868,0.03164352,0.0009843361,0.0005939803,0.0009184547,0.007754521,0.0180615],"genre_scores_gemma":[0.3773951,0.01062997,0.5879025,0.008269788,0.0007322602,0.001628208,0.002247684,0.001992084,0.009202377],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02394812,"threshold_uncertainty_score":0.1266513,"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."}}