{"id":"W2568818165","doi":"10.1016/j.ijmedinf.2017.01.001","title":"Text mining approach to predict hospital admissions using early medical records from the emergency department","year":2017,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":144,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Bigram; Trigram; Computer science; Decision tree; Artificial intelligence; Emergency department; Support vector machine; Naive Bayes classifier; Overcrowding; Machine learning; Data mining; 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":[0.0007736871,0.0006632101,0.0008339193,0.004900748,0.0005292542,0.001103168,0.0007907053,0.0008195564,0.0013012],"category_scores_gemma":[0.002581252,0.0001818944,0.001030825,0.002924271,0.0001231249,0.0008025431,0.0004698074,0.0008677114,0.0008610171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004027652,"about_ca_system_score_gemma":0.001067043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003906953,"about_ca_topic_score_gemma":0.006783131,"domain_scores_codex":[0.9993637,0.00009894015,0.0001479871,0.0001561972,0.0001550285,0.00007816047],"domain_scores_gemma":[0.997617,0.001315259,0.0003087887,0.00008700389,0.0005261964,0.0001458392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002259557,0.004207902,0.446986,0.001230595,0.0008891772,0.003536535,0.0005099299,0.01747208,0.01769849,0.00121505,0.01830457,0.4856901],"study_design_scores_gemma":[0.0002887551,0.002116446,0.3227565,0.0004930348,0.001508164,0.004151074,0.001958164,0.6273575,0.01840559,0.006144777,0.01467237,0.0001475828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.882648,0.003425246,0.07203784,0.002340918,0.00054604,0.0008475637,0.03164794,0.001626125,0.004880296],"genre_scores_gemma":[0.912447,0.00112038,0.06149184,0.0003053577,0.0003789334,0.0003315864,0.02166695,0.0000282754,0.00222962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004900748,"threshold_uncertainty_score":0.007768452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04215615082497658,"score_gpt":0.36154684623947,"score_spread":0.3193906954144934,"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."}}