{"id":"W2998776966","doi":"10.23919/cinc49843.2019.9005699","title":"An Algorithm for Early Detection of Sepsis Using Traditional Statistical Regression Modeling","year":2019,"lang":"en","type":"article","venue":"Computing in Cardiology Conference","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Logistic regression; Receiver operating characteristic; Cutoff; Constant false alarm rate; Computer science; Population; Data set; Regression; Statistics; ALARM; Artificial intelligence; False alarm; Test set; Algorithm; Data mining; Machine learning; Medicine; Mathematics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002103577,0.000100048,0.0004009552,0.00009201224,0.00003653754,0.000006483207,0.00004618429,0.0001084032,0.000009725006],"category_scores_gemma":[0.00004166086,0.00008667683,0.00007029798,0.00006147741,0.00004118212,0.00003520021,0.00001456586,0.000108814,0.000001545377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007350569,"about_ca_system_score_gemma":0.00008063683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005001297,"about_ca_topic_score_gemma":0.000001386299,"domain_scores_codex":[0.9991339,0.00008063782,0.0002466024,0.0002746225,0.00009955253,0.0001646968],"domain_scores_gemma":[0.9993033,0.0002815069,0.00006664921,0.0001537619,0.0001446171,0.00005009996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002425565,0.0003910214,0.5621288,0.0001501179,0.0002683824,0.00004664961,0.0005797811,0.05859573,0.0327016,0.001232192,0.000009868129,0.3436533],"study_design_scores_gemma":[0.001072891,0.0005260803,0.1388411,0.0001760774,0.0000538718,0.00003555441,0.00005556733,0.8573278,0.001068141,0.000772928,0.000001860796,0.0000681638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5653266,0.0000413931,0.4342307,0.000009413418,0.0001389033,0.0001860096,0.00001450638,0.00001059799,0.00004188082],"genre_scores_gemma":[0.9574448,0.000006494986,0.04235292,0.00002746878,0.0001006464,0.000008782927,0.00004839031,0.000009357888,0.000001080003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.798732,"threshold_uncertainty_score":0.3534579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1889821755872461,"score_gpt":0.3816623792290731,"score_spread":0.1926802036418271,"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."}}