{"id":"W4282962132","doi":"10.2196/37689","title":"Identifying the Risk of Sepsis in Patients With Cancer Using Digital Health Care Records: Machine Learning–Based Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; Korea Institute of Science and Technology Information; Samsung; National Supercomputing Center, Korea Institute of Science and Technology Information; Korea Institute of Science and Technology; National Research Foundation","keywords":"Medicine; Sepsis; Receiver operating characteristic; Logistic regression; Cancer; Medical prescription; Machine learning; Medical record; Random forest; Emergency medicine; Intensive care medicine; Artificial intelligence; Internal medicine; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777059,0.00087052,0.0009421966,0.005629067,0.0004724008,0.001571682,0.0009259608,0.001072677,0.0009973866],"category_scores_gemma":[0.006517752,0.0002937,0.001208979,0.00247942,0.0002851773,0.001146951,0.000830246,0.001257763,0.0003476112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107028,"about_ca_system_score_gemma":0.001141245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01109737,"about_ca_topic_score_gemma":0.01056131,"domain_scores_codex":[0.9987187,0.0004824095,0.0001362915,0.0003908271,0.0001574033,0.0001143788],"domain_scores_gemma":[0.9957342,0.002686705,0.0007276398,0.0002046667,0.0004578961,0.0001889335],"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":[0.0003632871,0.001223331,0.6953071,0.0002402131,0.0008383213,0.000535888,0.0001669151,0.1325877,0.0007892965,0.001078596,0.004150059,0.1627193],"study_design_scores_gemma":[0.00002387315,0.0001177363,0.04427642,0.00007137422,0.0001901643,0.0001791528,0.0001366777,0.9507344,0.0004097749,0.00298982,0.0008450845,0.00002550447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7893193,0.00444824,0.1846863,0.007293593,0.000245794,0.0005625929,0.007543008,0.001120371,0.00478087],"genre_scores_gemma":[0.9678054,0.0006672063,0.0273468,0.0003171623,0.0001983211,0.0001039762,0.003060098,0.00001359681,0.0004874696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01109737,"threshold_uncertainty_score":0.02206558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04534682778296099,"score_gpt":0.3433839276553197,"score_spread":0.2980370998723587,"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."}}