{"id":"W4390607161","doi":"10.1016/j.nuclcard.2024.101797","title":"Machine and deep learning models for accurate detection of ischemia and scar with myocardial blood flow positron emission tomography imaging","year":2024,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hospital for Sick Children; University of Ottawa","funders":"GE Healthcare; Canadian Institutes of Health Research; University of Ottawa Heart Institute Foundation; Lantheus Medical Imaging","keywords":"Medicine; Random forest; Artificial intelligence; Positron emission tomography; Coronary artery disease; Convolutional neural network; Logistic regression; Blood flow; Receiver operating characteristic; Perfusion scanning; Machine learning; Perfusion; Nuclear medicine; Radiology; Internal medicine; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001169931,0.0009509909,0.001014295,0.0007013672,0.0003403133,0.0008972851,0.001188157,0.001487558,0.0009644616],"category_scores_gemma":[0.003039164,0.0005888517,0.0007866668,0.0005142946,0.0003683674,0.0008352633,0.0008254982,0.001845126,0.0004479213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008226971,"about_ca_system_score_gemma":0.0008850486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01104776,"about_ca_topic_score_gemma":0.01051605,"domain_scores_codex":[0.9997439,0.00006690054,0.00001907462,0.00007348513,0.00004454855,0.00005203704],"domain_scores_gemma":[0.9989003,0.0006703766,0.00009541521,0.00007062938,0.0002198615,0.00004348028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003034463,0.0002152645,0.004633409,0.00008221356,0.0001246736,0.0001285077,0.00004941687,0.6431097,0.004348674,0.004122403,0.004687911,0.3381943],"study_design_scores_gemma":[0.000002420431,0.000008682251,0.0001536246,0.000003006418,0.00000398259,0.000007188077,0.000001931605,0.9985481,0.0003066492,0.000877916,0.00008428591,0.00000206179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1445042,0.003972305,0.8453088,0.001566955,0.0002241643,0.00007973191,0.0006375095,0.001838836,0.001867583],"genre_scores_gemma":[0.8697214,0.0009811565,0.1228861,0.0003566347,0.0001445943,0.0001007503,0.0009032099,0.00009103924,0.004815098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01104776,"threshold_uncertainty_score":0.02196687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006690263562314336,"score_gpt":0.2321033867211516,"score_spread":0.2254131231588372,"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."}}