{"id":"W3116361237","doi":"10.1016/j.compbiomed.2020.104182","title":"Identifying subpopulations of septic patients: A temporal data-driven approach","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"DBSCAN; Cluster analysis; Hierarchical clustering; Computer science; Sepsis; Intensive care unit; Data mining; Silhouette; Metric (unit); Medicine; Intensive care medicine; Artificial intelligence; Internal medicine; Engineering; Correlation clustering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001356993,0.00006052172,0.0001928109,0.000034176,0.00003800063,9.401017e-7,0.0001917337,0.00005888871,0.0001068936],"category_scores_gemma":[0.00004950448,0.0000462167,0.00001154143,0.0001946136,0.0004149624,0.00006468256,0.0002574336,0.00008492492,0.000006610597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008074381,"about_ca_system_score_gemma":0.00000232307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001522459,"about_ca_topic_score_gemma":0.00004675303,"domain_scores_codex":[0.9993606,0.00006953698,0.0001887263,0.0002417538,0.00004435766,0.00009506357],"domain_scores_gemma":[0.9996927,0.00004556562,0.00006136554,0.0001448358,0.000003027261,0.00005247985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001055561,0.00003036967,0.9959925,0.000008543407,0.00001500235,0.000001325448,0.000793401,0.0003743955,0.00007866173,0.0001768825,0.0008943542,0.001624043],"study_design_scores_gemma":[0.001313461,0.0002581953,0.755162,0.0000212082,0.00006569686,0.00000257383,0.0001302325,0.2400557,0.000004020116,0.001693605,0.001176708,0.0001166017],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590474,0.0001189156,0.03836939,0.001244543,0.00008643599,0.00009375892,0.000005537509,0.00001182792,0.00102215],"genre_scores_gemma":[0.9928679,0.00002111334,0.006110339,0.0007113568,0.00003448191,0.000001405154,0.0002462812,0.000002060709,0.000005000946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2408305,"threshold_uncertainty_score":0.1884663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0506968495238665,"score_gpt":0.3129302391844497,"score_spread":0.2622333896605832,"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."}}