{"id":"W1548451947","doi":"","title":"Acute hypotension episode prediction using information divergence for feature selection, and non-parametric methods for classification","year":2009,"lang":"en","type":"article","venue":"Computers in Cardiology Conference","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carré Technologies (Canada)","funders":"","keywords":"Discriminative model; Divergence (linguistics); Event (particle physics); Pattern recognition (psychology); Artificial intelligence; Computer science; Feature selection; Parametric statistics; Kullback–Leibler divergence; Training set; Nonparametric statistics; Set (abstract data type); Data set; Feature (linguistics); Test set; Feature extraction; Data mining; Statistics; Mathematics","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":[0.0004089932,0.0001169787,0.0003178882,0.0002496532,0.0001058989,0.00001973092,0.00005708802,0.0002113365,2.089574e-7],"category_scores_gemma":[0.0001263795,0.0001104056,0.00005901228,0.00023848,0.00003453455,0.000157997,0.00001229315,0.000150523,2.681766e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001100637,"about_ca_system_score_gemma":0.00006555469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006297614,"about_ca_topic_score_gemma":3.181009e-7,"domain_scores_codex":[0.9992514,0.00006786051,0.0002206369,0.0002240708,0.00005626145,0.0001797538],"domain_scores_gemma":[0.9992197,0.0001979318,0.00009778661,0.0001311598,0.0003000124,0.00005338073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007636044,0.00003998229,0.06289337,0.0001105909,0.000196798,0.000002008258,0.0003899509,0.003773618,0.06573798,0.001000678,0.0006537287,0.8644377],"study_design_scores_gemma":[0.00111964,0.0004268119,0.2244891,0.00005221239,0.00007182533,0.00008228955,0.00001760304,0.7708468,0.0008342862,0.001375234,0.0005973681,0.00008678723],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2442629,0.00005305013,0.7541068,0.0003004716,0.0006219099,0.0005882463,0.00001110224,0.00003576147,0.00001971256],"genre_scores_gemma":[0.6812941,0.0001117942,0.3182476,0.000114246,0.0001270818,0.0000266336,0.00007016493,0.00000364123,0.000004809248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8643509,"threshold_uncertainty_score":0.4502209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04459204395439844,"score_gpt":0.3644855153392511,"score_spread":0.3198934713848526,"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."}}