{"id":"W3021373785","doi":"10.1186/s12911-020-1101-8","title":"Machine learning approaches to predict peak demand days of cardiovascular admissions considering environmental exposure","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Climate Change and Health Impacts","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Key Research and Development Program of Sichuan Province; West China Hospital, Sichuan University; Sichuan University; National Natural Science Foundation of China","keywords":"Machine learning; Support vector machine; Random forest; Gradient boosting; Artificial intelligence; Logistic regression; Receiver operating characteristic; Predictive modelling; Artificial neural network; Medicine; Computer science; Boosting (machine learning); Ensemble forecasting","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":[0.003425902,0.001111317,0.001110615,0.002985862,0.0004010218,0.0009637663,0.001268782,0.0009726107,0.001042758],"category_scores_gemma":[0.005510235,0.0003351919,0.001337693,0.001516633,0.0002570126,0.0007197525,0.0006948933,0.001286005,0.0003111001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009562059,"about_ca_system_score_gemma":0.001507703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009760611,"about_ca_topic_score_gemma":0.006100446,"domain_scores_codex":[0.9989993,0.0003995509,0.0001003809,0.0002143197,0.0001599053,0.0001265386],"domain_scores_gemma":[0.9971789,0.001844907,0.0003405307,0.00006920099,0.00046336,0.0001031054],"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":[0.0002207566,0.0004799341,0.1091248,0.000187962,0.0004475839,0.0001999144,0.00009484787,0.7653303,0.0005795205,0.0008948167,0.002231304,0.1202082],"study_design_scores_gemma":[0.00000880413,0.00004470146,0.005237612,0.00002205751,0.0000339349,0.00002115708,0.0000271252,0.9933879,0.0001242807,0.0008641306,0.0002209051,0.000007309754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6346461,0.005672666,0.3496556,0.002319421,0.0003113028,0.0003435334,0.001760908,0.00131379,0.003976717],"genre_scores_gemma":[0.973566,0.000515636,0.02395945,0.0001365223,0.0001281717,0.0001402185,0.0008796524,0.00001939361,0.0006549121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009760611,"threshold_uncertainty_score":0.01940763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1443994186192021,"score_gpt":0.2918378898689514,"score_spread":0.1474384712497492,"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."}}