{"id":"W4224055553","doi":"10.1108/imds-12-2021-0769","title":"Making the hospital smart: using a deep long short-term memory model to predict hospital performance metrics","year":2022,"lang":"en","type":"article","venue":"Industrial Management & Data Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Recurrent neural network; Computer science; Autoregressive integrated moving average; Mean squared error; Mean absolute percentage error; Medical prescription; Autoregressive model; Time series; Artificial intelligence; Term (time); Artificial neural network; Machine learning; Data mining; Statistics; Medicine; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001130841,0.0003358854,0.0003166025,0.0003426973,0.0005446815,0.0003525928,0.00183375,0.00009242507,0.00002154458],"category_scores_gemma":[0.00003617288,0.0003110752,0.00006684356,0.001024267,0.00002739184,0.0006104686,0.002207518,0.0005664805,0.000009617921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003787546,"about_ca_system_score_gemma":0.00002748727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007916836,"about_ca_topic_score_gemma":0.000007096417,"domain_scores_codex":[0.9973254,0.00008751882,0.0006039278,0.0005377356,0.0008197324,0.0006257407],"domain_scores_gemma":[0.9983807,0.00005951593,0.0001080338,0.001317349,0.00002663031,0.000107837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001410777,0.00004182276,0.00490181,0.0001162587,0.0002374334,0.00006838239,0.0004237394,0.9722228,0.000009917015,0.00008919329,0.006776588,0.01509792],"study_design_scores_gemma":[0.0004170657,0.0001061295,0.000252759,0.0001845341,0.0001517523,0.00001581876,0.0009520394,0.9899572,0.000008478407,0.000001620265,0.00752811,0.0004244856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388218,0.0009361179,0.04022421,0.00005432295,0.01207195,0.002070547,0.0004752038,0.0004980394,0.004847803],"genre_scores_gemma":[0.9978412,0.00002396637,0.0003402802,0.00002529265,0.00105421,0.0001873732,0.0002665117,0.00008728074,0.0001739247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05901935,"threshold_uncertainty_score":0.9999341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1019509993021668,"score_gpt":0.2622060953328756,"score_spread":0.1602550960307089,"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."}}