{"id":"W2925214600","doi":"10.2147/ijnrd.s194727","title":"<p>Prediction of cardiovascular outcomes with machine learning techniques: application to the Cardiovascular Outcomes in Renal Atherosclerotic Lesions (CORAL) study</p>","year":2019,"lang":"en","type":"article","venue":"International Journal of Nephrology and Renovascular Disease","topic":"Chronic Kidney Disease and Diabetes","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Heart, Lung, and Blood Institute; AstraZeneca; Cordis; National Institutes of Health; Pfizer","keywords":"Random forest; Medicine; Machine learning; Logistic regression; Artificial intelligence; Decision tree; Support vector machine; Population; Creatinine; Receiver operating characteristic; Artificial neural network; Internal medicine; Statistics; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01005752,0.0005551454,0.0005547871,0.0008281936,0.0001468289,0.0005002739,0.0005491609,0.0003111814,0.001639363],"category_scores_gemma":[0.01651336,0.0002313065,0.001047416,0.0006947572,0.0002505921,0.0002134846,0.0006780053,0.0007336058,0.000379393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002897625,"about_ca_system_score_gemma":0.0007680371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003496308,"about_ca_topic_score_gemma":0.004256662,"domain_scores_codex":[0.9976529,0.001795973,0.00006815817,0.0001509193,0.0002860116,0.00004604144],"domain_scores_gemma":[0.9898401,0.006741344,0.001164601,0.001372031,0.0006091476,0.0002727336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005393398,0.0003375733,0.791042,0.000555227,0.002453962,0.0005681933,0.0003656554,0.02632001,0.003162576,0.0005873934,0.009853809,0.1593602],"study_design_scores_gemma":[0.002017707,0.004061974,0.7790093,0.0001790485,0.001670976,0.00121194,0.0002260169,0.1977722,0.004230128,0.002077331,0.007444017,0.00009931898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9539328,0.001351502,0.03678525,0.001163094,0.00005135726,0.0005850047,0.002849536,0.0006438108,0.00263766],"genre_scores_gemma":[0.939939,0.0005036101,0.05560463,0.0001393586,0.00006191087,0.0005266074,0.002441182,0.000110286,0.0006734069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01005752,"threshold_uncertainty_score":0.05318993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009181386730897847,"score_gpt":0.2425915154984641,"score_spread":0.2334101287675663,"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."}}