{"id":"W4389305820","doi":"10.1016/j.jtcvs.2023.11.048","title":"Commentary: Optimizing transfusion and hemostasis practices in cardiac surgery: Human versus machine or human and machine?","year":2023,"lang":"en","type":"editorial","venue":"Journal of Thoracic and Cardiovascular Surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Thromboelastography; Hemostasis; Interpretability; Medicine; Cardiopulmonary bypass; Cardiac surgery; Fibrinogen; Intensive care medicine; Computer science; Coagulation; Machine learning; Artificial intelligence; Surgery; Cardiology; Internal medicine","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":[0.01310038,0.003030951,0.005118909,0.002803419,0.004872936,0.007946767,0.004879387,0.05510694,0.01233116],"category_scores_gemma":[0.07870153,0.001842333,0.002982662,0.002174313,0.003776963,0.004632158,0.002106139,0.05143119,0.009561408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006154231,"about_ca_system_score_gemma":0.01031756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00643476,"about_ca_topic_score_gemma":0.01526055,"domain_scores_codex":[0.9900559,0.002760815,0.001460623,0.001076471,0.00395378,0.0006923376],"domain_scores_gemma":[0.9416534,0.03298702,0.003263229,0.001152301,0.01531806,0.00562606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003454071,0.000009242528,0.00002223776,0.0001468532,0.00002317969,0.00006085769,0.0000153057,0.00001756312,0.00001788002,0.000158885,0.9978526,0.001640861],"study_design_scores_gemma":[0.0003593193,0.00006734167,0.0006122577,0.001957867,0.0002784001,0.0003325854,0.0001509806,0.0003566457,0.0001365072,0.002957558,0.9927288,0.00006172204],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.00005705645,0.004859518,0.0001071661,0.2843152,0.7087977,0.00003535304,0.000133717,0.00004133559,0.001652907],"genre_scores_gemma":[0.0006520587,0.002666831,0.0001610883,0.1786316,0.8137412,0.00006399278,0.00004393816,0.00003450272,0.004004763],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.05510694,"threshold_uncertainty_score":0.06928229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1838759374466049,"score_gpt":0.439133033436663,"score_spread":0.2552570959900582,"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."}}