{"id":"W4200250868","doi":"10.3389/fcvm.2021.711401","title":"Implementing Machine Learning in Interventional Cardiology: The Benefits Are Worth the Trouble","year":2021,"lang":"en","type":"review","venue":"Frontiers in Cardiovascular Medicine","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Montreal Heart Institute","funders":"Institut de Valorisation des Données; Institut de Cardiologie de Montréal; Fondation Institut de Cardiologie de Montréal","keywords":"Interventional cardiology; Interpretability; Medicine; Generalizability theory; Artificial intelligence; Cardiac imaging; Medical physics; Percutaneous coronary intervention; Machine learning; Internal medicine; Computer science; Myocardial infarction","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007339651,0.0006461273,0.00560769,0.0006098934,0.0002312116,0.00004248476,0.0004491437,0.000333695,0.00005285718],"category_scores_gemma":[0.002769429,0.0003625293,0.004108807,0.001462325,0.0003436336,0.00004970024,0.0004256103,0.002746024,0.000007311229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004818413,"about_ca_system_score_gemma":0.0003547215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003388107,"about_ca_topic_score_gemma":0.00009192162,"domain_scores_codex":[0.9942136,0.001609703,0.001335277,0.0008607786,0.001086359,0.0008943304],"domain_scores_gemma":[0.997205,0.0006762893,0.0003955594,0.00141377,0.0001795087,0.0001298474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001221751,0.00003519562,0.09158352,0.003160291,0.005403388,0.001100327,0.0001591139,0.0005454318,1.014826e-8,0.00003087554,0.01401163,0.883958],"study_design_scores_gemma":[0.001886739,0.00005301842,0.009421403,0.0325982,0.007298916,0.0009700322,0.001210889,0.00007321204,6.778144e-8,0.00001389426,0.9461746,0.0002990486],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001014212,0.9919671,0.001755417,0.0009825884,0.002738139,0.00135561,0.00004254338,0.0000526304,0.001095851],"genre_scores_gemma":[0.0004138248,0.9952768,0.0002314967,0.0002108574,0.002131905,0.0003565033,0.0009636588,0.0001082146,0.0003067434],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9321629,"threshold_uncertainty_score":0.9998826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03721451777243195,"score_gpt":0.3110757839357709,"score_spread":0.2738612661633389,"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."}}