{"id":"W2759098891","doi":"10.1109/bibm47256.2019.8983087","title":"Predicting Emergency Department Visits Based on Cancer Patient Types","year":2019,"lang":"en","type":"article","venue":"","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Toronto; Microsoft (Canada)","funders":"","keywords":"Logistic regression; Emergency department; Medicine; Retrospective cohort study; Cancer; Regression analysis; Emergency medicine; Regression; Cohort; Medical emergency; Statistics; Computer science; Machine learning; Internal medicine","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":[0.000976356,0.0002270715,0.0003219773,0.001337914,0.0002237391,0.0005355735,0.0003034576,0.0002839602,0.001332042],"category_scores_gemma":[0.009544832,0.0001551478,0.000513811,0.001012422,0.0001768224,0.0003563547,0.000588744,0.0004306285,0.0001797229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002449422,"about_ca_system_score_gemma":0.0003160359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003735569,"about_ca_topic_score_gemma":0.004870248,"domain_scores_codex":[0.9993048,0.0002723429,0.00009392236,0.0001227178,0.000126159,0.00008009279],"domain_scores_gemma":[0.9939048,0.002199037,0.002531602,0.0004161677,0.0004756076,0.000472778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005994253,0.000007860493,0.9983733,0.000005489104,0.00001716066,0.00001917502,0.00001324722,0.0002039772,0.00003645941,0.00001170535,0.00006895094,0.001182883],"study_design_scores_gemma":[0.000007641774,0.00008108807,0.9955379,0.00001893572,0.0000341365,0.0003301523,0.0001958514,0.003245647,0.0001803621,0.0001061745,0.0002550641,0.000007121402],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99792,0.0001670038,0.0005110808,0.00008868558,0.00001327296,0.00002133215,0.0008956405,0.00001210238,0.0003709708],"genre_scores_gemma":[0.9987305,0.00005089873,0.0005614685,0.0000188031,0.00001031969,0.000008624924,0.0005517117,0.000001879441,0.00006577576],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003735569,"threshold_uncertainty_score":0.007427633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03572789442726843,"score_gpt":0.3265865614072023,"score_spread":0.2908586669799339,"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."}}