{"id":"W4282921422","doi":"10.1177/14604582221106396","title":"Comparative analysis of machine learning approaches for predicting frequent emergency department visits","year":2022,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Research Foundation of Korea","keywords":"Random forest; Overcrowding; Emergency department; Support vector machine; Machine learning; Logistic regression; Artificial intelligence; Computer science; Statistical classification; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001408957,0.0001301041,0.0006536309,0.0003845739,0.001027158,0.000006450116,0.00008866588,0.00001963096,0.0002479728],"category_scores_gemma":[0.00009316553,0.0001084652,0.00029082,0.0006160597,0.00001764234,0.00009899338,0.00007987212,0.00049479,6.440371e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002069091,"about_ca_system_score_gemma":0.0001883695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001423105,"about_ca_topic_score_gemma":0.00002044066,"domain_scores_codex":[0.9975709,0.00009567135,0.001480694,0.00007082678,0.0004758859,0.0003060763],"domain_scores_gemma":[0.998309,0.00005855389,0.001155242,0.0001042271,0.0002043333,0.000168683],"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":[0.0008195202,0.0009012166,0.4592417,0.003045491,0.01664471,0.000009028491,0.202321,0.2652553,0.00002696613,0.001789913,0.02925471,0.02069042],"study_design_scores_gemma":[0.002378725,0.004436634,0.02674503,0.0001150947,0.002681911,0.0001861,0.06961439,0.8266773,0.00007997182,0.0001522183,0.06662568,0.0003069128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9130824,0.02133532,0.05117094,0.003341396,0.001496963,0.002160681,0.0007690982,0.00008511193,0.006558156],"genre_scores_gemma":[0.9908626,0.001990603,0.006267883,0.0003171163,0.00009434472,0.00007011743,0.0002919555,0.000008098025,0.00009728491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.561422,"threshold_uncertainty_score":0.7900171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09256502616697647,"score_gpt":0.3667117608685213,"score_spread":0.2741467347015448,"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."}}