{"id":"W3004717216","doi":"10.1016/j.cjca.2020.02.002","title":"The Rise of Open-Sourced Machine Learning in Small and Imbalanced Datasets: Predicting In-Stent Restenosis","year":2020,"lang":"en","type":"letter","venue":"Canadian Journal of Cardiology","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; Fonds de Recherche du Québec - Santé; National Institutes of Health","keywords":"Restenosis; Medicine; Scopus; Stent; Percutaneous coronary intervention; Internal medicine; Cardiology; Angina; MEDLINE; Myocardial infarction","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01909267,0.0006159252,0.00289521,0.001401806,0.001046274,0.006919218,0.002864409,0.016636,0.00364677],"category_scores_gemma":[0.1614269,0.0006467427,0.001227792,0.001958958,0.003293507,0.007833062,0.001950264,0.02192802,0.003782512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003100392,"about_ca_system_score_gemma":0.002380604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003034873,"about_ca_topic_score_gemma":0.006593434,"domain_scores_codex":[0.9829605,0.007088037,0.001911422,0.002269547,0.005048601,0.000721951],"domain_scores_gemma":[0.7271447,0.2216603,0.00717772,0.007124081,0.02635464,0.01053856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004787339,0.00009685824,0.008185213,0.0003991623,0.0001670809,0.001300402,0.0002220675,0.0008418159,0.0007021247,0.006217174,0.7867314,0.1946579],"study_design_scores_gemma":[0.0006507583,0.000417018,0.01557642,0.002068016,0.0002994919,0.008618968,0.0008312065,0.0307804,0.002142139,0.1579753,0.7802765,0.0003637591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.002416069,0.008383324,0.00461779,0.9643068,0.01776504,0.00001912716,0.0005970655,0.0002518524,0.001642928],"genre_scores_gemma":[0.06226433,0.01341125,0.01501223,0.7255199,0.1788447,0.0001961407,0.001223356,0.0004603821,0.003067749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01909267,"threshold_uncertainty_score":0.1009729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02989552522806916,"score_gpt":0.2661559051783901,"score_spread":0.2362603799503209,"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."}}