{"id":"W4399207734","doi":"10.1016/j.cjca.2024.05.024","title":"Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide","year":2024,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; McGill University; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute; Montreal Heart Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Fonds de Recherche du Québec-Société et Culture; Institut de Valorisation des Données; Canadian Institute for Advanced Research; Novo Nordisk; European Society of Cardiology; Fonds de Recherche du Québec - Santé; Alberta Innovates - Health Solutions; Canadian Cardiovascular Society","keywords":"Medicine; Interpretation (philosophy); Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.01837385,0.001924254,0.001036959,0.003405021,0.001330299,0.008300013,0.003867535,0.003748063,0.02044697],"category_scores_gemma":[0.06881839,0.001924804,0.001866043,0.002269953,0.003624009,0.01260808,0.007717099,0.007973271,0.01248538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002787391,"about_ca_system_score_gemma":0.006181435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004784545,"about_ca_topic_score_gemma":0.008347414,"domain_scores_codex":[0.9873131,0.008359279,0.001060038,0.0008994414,0.002129985,0.0002380683],"domain_scores_gemma":[0.9599149,0.02970137,0.001077573,0.004374609,0.004178949,0.0007526345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001091202,0.0001744828,0.001376177,0.001034865,0.0000863852,0.000690312,0.00157091,0.022183,0.003658957,0.4410661,0.09640173,0.4316481],"study_design_scores_gemma":[0.00006553584,0.00005247469,0.0002544547,0.0009486498,0.00003692929,0.000448888,0.0006462059,0.1213277,0.00257332,0.6488357,0.2247013,0.0001089373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001090132,0.003386081,0.9556507,0.02425804,0.0002553279,0.0003540248,0.0005165138,0.003159717,0.01132946],"genre_scores_gemma":[0.01354505,0.002588568,0.9764705,0.001732142,0.0003236265,0.0005840409,0.0004410332,0.0007081637,0.003606905],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02044697,"threshold_uncertainty_score":0.09717137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.241870077088214,"score_gpt":0.4848485311834558,"score_spread":0.2429784540952418,"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."}}