{"id":"W2031917779","doi":"10.1007/s12350-014-0027-x","title":"Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population","year":2014,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; Cedars-Sinai Medical Center","keywords":"Medicine; Revascularization; Myocardial perfusion imaging; Coronary artery disease; Supine position; Cardiology; Internal medicine; Ejection fraction; Perfusion; Radiology; Myocardial infarction; Heart failure","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":[0.0009326638,0.00008386029,0.0005073074,0.0002066523,0.00002628212,0.000005812903,0.00003129468,0.0001018538,0.00002420702],"category_scores_gemma":[0.0009623588,0.00007367242,0.000280945,0.0001175719,0.00002518616,0.00006833178,0.0000246654,0.0003498365,0.000004476936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000077414,"about_ca_system_score_gemma":0.0000190157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002548848,"about_ca_topic_score_gemma":0.000001139764,"domain_scores_codex":[0.9988344,0.0003001647,0.000410661,0.0001046013,0.0002182019,0.0001319629],"domain_scores_gemma":[0.9994042,0.0000795024,0.0002172221,0.0001110435,0.0001309722,0.0000570587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004106679,0.0000423754,0.9905735,0.00003016466,0.00006958043,0.00003965903,0.000136153,0.0009382301,0.004618352,0.00002906983,0.001126453,0.001985851],"study_design_scores_gemma":[0.002191385,0.0005782271,0.9776824,0.0001162145,0.0002222194,0.0005769972,0.00004346796,0.003536952,0.00003392188,0.00003552052,0.01492862,0.00005415006],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953782,0.0007708756,0.002235618,0.000312435,0.0004430576,0.00009241088,0.00001244078,0.00001459036,0.0007403945],"genre_scores_gemma":[0.9987058,0.0002779847,0.0002293948,0.0001430292,0.0005643878,6.97527e-7,0.00004331861,0.00002003928,0.00001537067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01380217,"threshold_uncertainty_score":0.3004274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006268616767209741,"score_gpt":0.2213243754205957,"score_spread":0.2150557586533859,"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."}}