{"id":"W3132080324","doi":"10.21203/rs.3.rs-153020/v1","title":"Machine Learning Based Prediction Model for Using Non-steroidal Anti-inflammatory Drugs on Risk of Adverse Events","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Inflammatory mediators and NSAID effects","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Department of Health, Government of Western Australia","keywords":"Acute coronary syndrome; Medicine; Adverse effect; Machine learning; Support vector machine; Gradient boosting; Receiver operating characteristic; Cohort; Boosting (machine learning); Population; Artificial intelligence; Predictive modelling; Emergency medicine; Intensive care medicine; Internal medicine; Computer science; Myocardial infarction","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":[0.002901708,0.0007701393,0.0008930762,0.001277101,0.000272316,0.001234691,0.0008593304,0.0009690329,0.003823964],"category_scores_gemma":[0.008263689,0.000362499,0.0008512228,0.0007352722,0.0002984187,0.0006268895,0.0003980402,0.0009509252,0.0008796628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001096099,"about_ca_system_score_gemma":0.001147336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01913266,"about_ca_topic_score_gemma":0.008068343,"domain_scores_codex":[0.9993647,0.0002424791,0.00004667455,0.0001371796,0.0001111701,0.00009779064],"domain_scores_gemma":[0.9960719,0.002889108,0.0003306421,0.00007669363,0.0005321157,0.00009954507],"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":[0.0007080581,0.0005588896,0.1178697,0.00009073262,0.000271608,0.000348159,0.00009874203,0.8393182,0.0007858108,0.001899738,0.00231226,0.03573819],"study_design_scores_gemma":[0.00001433385,0.00004311437,0.004037806,0.000007638531,0.00001861663,0.00002019551,0.000009000699,0.9951876,0.00008870377,0.000476767,0.00009097817,0.000005177862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.886439,0.0007829068,0.1033944,0.001928271,0.0001747086,0.0001985284,0.002170162,0.0008203474,0.004091833],"genre_scores_gemma":[0.9867712,0.0001436594,0.009477746,0.0000640982,0.00004437138,0.0001292157,0.0008524925,0.00001437241,0.002502863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01913266,"threshold_uncertainty_score":0.03804255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04165511747306669,"score_gpt":0.3583109251263006,"score_spread":0.316655807653234,"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."}}