{"id":"W3128825412","doi":"10.1186/s13040-021-00235-0","title":"Data analytics and clinical feature ranking of medical records of patients with sepsis","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Krembil Foundation","funders":"University of Toronto","keywords":"Sepsis; Medical record; Septic shock; Medicine; Context (archaeology); Ranking (information retrieval); Electronic medical record; Machine learning; Binary classification; Computer science; Logistic regression; SOFA score; Artificial intelligence; Intensive care medicine; Data mining; Emergency medicine; Internal medicine; Support vector machine","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":[0.0004206733,0.00009859974,0.0004385634,0.00004677206,0.00002213673,0.000009260788,0.0001604161,0.0001266117,0.0001636163],"category_scores_gemma":[0.0009935577,0.00006868263,0.00004090194,0.0001937242,0.0001076762,0.00006861632,0.000325594,0.0001176885,7.487097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001016451,"about_ca_system_score_gemma":0.0001862703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002709612,"about_ca_topic_score_gemma":0.00009029516,"domain_scores_codex":[0.998611,0.00004841631,0.0003584902,0.0003429938,0.0005242733,0.0001148233],"domain_scores_gemma":[0.9984432,0.0003529509,0.0001653561,0.0007696185,0.000138616,0.0001302433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009488151,0.0006131957,0.9565057,0.00007678131,0.0004291371,0.0000486165,0.00004787763,3.793018e-8,0.000002752848,0.000009242114,0.00601961,0.03615219],"study_design_scores_gemma":[0.003594867,0.0004758882,0.9871297,0.0008044874,0.0007790867,0.00001024747,0.0002996325,0.0003507899,0.0001979901,0.000001297284,0.006279586,0.000076366],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967834,0.0009448522,0.00004079502,0.001330638,0.00009577035,0.00009496078,0.0005632169,0.000006908987,0.0001394006],"genre_scores_gemma":[0.9805368,0.001036878,0.01552847,0.0003123064,0.00007804661,0.000001519526,0.002459916,0.00001362704,0.00003245137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03607582,"threshold_uncertainty_score":0.2800796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2182863075406786,"score_gpt":0.4170764311393291,"score_spread":0.1987901235986505,"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."}}