{"id":"W2964149875","doi":"10.1093/ehjci/jez177","title":"Machine learning predicts per-vessel early coronary revascularization after fast myocardial perfusion SPECT: results from multicentre REFINE SPECT registry","year":2019,"lang":"en","type":"article","venue":"European Heart Journal - Cardiovascular Imaging","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; Taipei Veterans General Hospital; Cedars-Sinai Medical Center","keywords":"Myocardial perfusion imaging; Medicine; Coronary artery disease; Receiver operating characteristic; Revascularization; Nuclear medicine; Area under the curve; Perfusion; Single-photon emission computed tomography; Confidence interval; Cardiology; Coronary angiography; Spect imaging; Internal medicine; Radiology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002837429,0.00059418,0.001170553,0.0003206722,0.0004222068,0.0004480999,0.0002426506,0.00007368141,0.0002003578],"category_scores_gemma":[0.001604818,0.0005634673,0.002455763,0.0003362964,0.0001247765,0.0004927996,0.0003192602,0.002090176,0.001161191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003138108,"about_ca_system_score_gemma":0.0001629419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002836541,"about_ca_topic_score_gemma":0.000001196338,"domain_scores_codex":[0.9939181,0.001508876,0.0009756311,0.001062044,0.001727909,0.0008075041],"domain_scores_gemma":[0.9969164,0.0002608621,0.0002926459,0.001483022,0.0004384096,0.0006086489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001797115,0.0001867884,0.9439349,0.0001238981,0.002111238,0.01450747,0.001928861,0.0059332,0.004289304,0.000001771339,0.004341386,0.0208441],"study_design_scores_gemma":[0.009727414,0.0001686767,0.8388974,0.001361422,0.001891288,0.009984924,0.0003707992,0.002737568,0.0002917379,0.000005219406,0.1339335,0.000630083],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390932,0.03726157,0.002523015,0.001367262,0.002686735,0.0008275966,0.0001424859,0.000381832,0.01571633],"genre_scores_gemma":[0.9890519,0.002042078,0.002126319,0.0005636314,0.004394474,0.000003714041,0.0004197729,0.0002567791,0.001141292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1295921,"threshold_uncertainty_score":0.9996817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009387806034765526,"score_gpt":0.2222651065920666,"score_spread":0.212877300557301,"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."}}