{"id":"W3005984647","doi":"10.1016/j.compbiomed.2020.103659","title":"Direct estimation of left ventricular ejection fraction via a cardiac cycle feature learning architecture","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Ejection fraction; Ventricle; Cardiac cycle; Cardiac Ventricle; Artificial intelligence; Cardiac magnetic resonance imaging; Fraction (chemistry); Cardiology; Computer science; Magnetic resonance imaging; Pattern recognition (psychology); Internal medicine; Medicine; Heart failure; Radiology; Chemistry","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":[0.0001900925,0.000102028,0.0004173182,0.0001351759,0.00004381601,0.000001461727,0.00002191537,0.0001507,0.00001450765],"category_scores_gemma":[0.0001650247,0.00007385421,0.00009103215,0.0001912518,0.0001033396,0.00002146219,0.00001889541,0.0003370807,0.000001496408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000283557,"about_ca_system_score_gemma":0.00001300346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003961057,"about_ca_topic_score_gemma":9.958369e-7,"domain_scores_codex":[0.9993212,0.0001288733,0.0001522308,0.0002101118,0.00008581427,0.0001017751],"domain_scores_gemma":[0.9996526,0.00008312063,0.00006797418,0.0000806223,0.00003148199,0.00008416974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007362745,0.00007096321,0.6766366,0.0003652049,0.000554487,0.00006951855,0.001907657,0.01014636,0.01893773,0.00007599676,0.001451118,0.289048],"study_design_scores_gemma":[0.006828023,0.003347219,0.8499728,0.0007179959,0.0007433901,0.0004437045,0.0007157074,0.06520065,0.004843414,0.0003267336,0.06647657,0.0003837795],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7539555,0.004279585,0.2350569,0.004545864,0.00112425,0.0003960632,0.000001818272,0.0001016205,0.0005384194],"genre_scores_gemma":[0.9977877,0.0004492211,0.0009296305,0.0003775506,0.0003428351,0.000002151636,0.00008989195,0.000006998894,0.00001400444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2886643,"threshold_uncertainty_score":0.3011688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006953386246605185,"score_gpt":0.2589669607386423,"score_spread":0.2520135744920372,"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."}}