{"id":"W3201570690","doi":"10.1038/s41598-021-97643-3","title":"Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Department of Health, Government of Western Australia","keywords":"Acute coronary syndrome; Medicine; Gradient boosting; Receiver operating characteristic; Machine learning; Boosting (machine learning); Population; Cohort; Support vector machine; Artificial intelligence; Emergency medicine; Internal medicine; Computer science; Myocardial infarction; Random forest","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":[0.005260416,0.0007556421,0.0009533355,0.001872811,0.0002973228,0.001165357,0.000913512,0.0008228567,0.001524252],"category_scores_gemma":[0.01299789,0.0003488551,0.0008672547,0.001096835,0.000279659,0.0006024259,0.0005503338,0.001268383,0.0006918283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003861,"about_ca_system_score_gemma":0.001273408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01564829,"about_ca_topic_score_gemma":0.008900857,"domain_scores_codex":[0.9987821,0.0006331946,0.00008633101,0.0002029022,0.0001641066,0.0001314237],"domain_scores_gemma":[0.9927516,0.005398966,0.0006571384,0.00022434,0.00079601,0.0001719126],"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":[0.001098201,0.001276193,0.4606943,0.0001333591,0.0006111319,0.0005421859,0.0002570233,0.4637753,0.0007915429,0.001956107,0.003865899,0.06499874],"study_design_scores_gemma":[0.0000325135,0.0001046901,0.02231334,0.00001822145,0.00005130089,0.00006187873,0.00003530861,0.9760178,0.0001370864,0.0009569613,0.000259559,0.00001135732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9404916,0.0006901309,0.05220362,0.001426734,0.0001089697,0.0002091093,0.00248154,0.0005928251,0.001795419],"genre_scores_gemma":[0.9839659,0.0001767657,0.01312435,0.00007060222,0.00005528097,0.0001542584,0.001494046,0.00001198773,0.0009469553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01564829,"threshold_uncertainty_score":0.03111446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0411760771981501,"score_gpt":0.2991261595307595,"score_spread":0.2579500823326094,"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."}}