{"id":"W2748190412","doi":"10.1093/cid/cix775","title":"Optimizing Empiric Antibiotic Selection in Sepsis: Turning Probabilities Into Practice","year":2017,"lang":"en","type":"letter","venue":"Clinical Infectious Diseases","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Sepsis; Selection (genetic algorithm); Intensive care medicine; Antibiotics; Internal medicine; Microbiology; Machine learning; Computer science","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":[0.008538363,0.000628091,0.001825959,0.0007843393,0.0008418647,0.00447512,0.001572619,0.009832799,0.002939394],"category_scores_gemma":[0.12112,0.0005670938,0.0008519727,0.0007362223,0.002652491,0.004089489,0.001437318,0.02365012,0.001625694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002584836,"about_ca_system_score_gemma":0.002542585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001721776,"about_ca_topic_score_gemma":0.002499844,"domain_scores_codex":[0.9932748,0.004333805,0.000712572,0.0005589454,0.0008799225,0.0002399892],"domain_scores_gemma":[0.9023555,0.08575901,0.002208455,0.001841094,0.005511486,0.002324359],"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":[0.00127032,0.0004030086,0.0178203,0.0005835046,0.0002939413,0.00380504,0.0004773266,0.0188769,0.001183699,0.04848434,0.5119764,0.3948253],"study_design_scores_gemma":[0.0007735661,0.0006017769,0.007918786,0.001981608,0.0002962943,0.004764274,0.000706554,0.08599445,0.002470063,0.6856323,0.2085754,0.0002849067],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"editorial","genre_scores_codex":[0.003681013,0.007294239,0.0139121,0.9650971,0.00585808,0.00001841063,0.00007932283,0.0001125452,0.003947221],"genre_scores_gemma":[0.262509,0.02368829,0.04441997,0.5273279,0.1381402,0.0001925907,0.0001387273,0.0003387478,0.003244512],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.009832799,"threshold_uncertainty_score":0.0451557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04100201286941735,"score_gpt":0.3754208071093416,"score_spread":0.3344187942399243,"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."}}