{"id":"W2800180260","doi":"10.1007/s12410-018-9453-5","title":"Application of Artificial Intelligence in Coronary Computed Tomography Angiography","year":2018,"lang":"en","type":"article","venue":"Current Cardiovascular Imaging Reports","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Coronary artery disease; Artificial intelligence; Medical diagnosis; Radiology; Fractional flow reserve; Angiography; Computed tomography angiography; Computed tomography; Machine learning; Coronary angiography; Medical physics; Computer science; Cardiology; 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":[],"consensus_categories":[],"category_scores_codex":[0.0007334183,0.0001935093,0.0005635711,0.0006263494,0.00004970162,0.00001949349,0.00007157062,0.0000425401,0.000008911841],"category_scores_gemma":[0.0001386097,0.0002015874,0.001562287,0.001225327,0.0003636033,0.00007762996,0.00006880871,0.0001870593,0.00001491824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004153606,"about_ca_system_score_gemma":0.00007636248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000107259,"about_ca_topic_score_gemma":0.000001696605,"domain_scores_codex":[0.99795,0.00006069649,0.0006508618,0.0005227012,0.0005282015,0.0002875878],"domain_scores_gemma":[0.9982606,0.00005371467,0.0001692949,0.0009798277,0.0004179553,0.0001186432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001849009,0.0001589104,0.692623,0.00008447094,0.0002370442,0.0001889214,0.00008250838,0.00009508272,0.0001338929,0.0000345372,0.0002846439,0.3060585],"study_design_scores_gemma":[0.0002119742,0.00003972074,0.9830635,0.0003827379,0.000746172,0.001373929,0.00006776246,0.002963606,0.002844584,0.000933559,0.00709975,0.0002726619],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2927881,0.1199482,0.5793178,0.0001345445,0.003642871,0.001595267,0.00001527672,0.0002846275,0.002273319],"genre_scores_gemma":[0.997642,0.00006336932,0.001735694,0.00003283997,0.0003801988,0.00003599925,0.00008322934,0.00002583624,8.206854e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.704854,"threshold_uncertainty_score":0.8220496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01467860462782998,"score_gpt":0.2807993166733442,"score_spread":0.2661207120455142,"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."}}