{"id":"W4405014239","doi":"10.1016/j.jcmg.2024.09.010","title":"Leveraging a Vision Transformer Model to Improve Diagnostic Accuracy of Cardiac Amyloidosis With Cardiac Magnetic Resonance","year":2024,"lang":"en","type":"article","venue":"JACC. Cardiovascular imaging","topic":"Amyloidosis: Diagnosis, Treatment, Outcomes","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Circle Cardiovascular Imaging; Kiniksa Pharmaceuticals; National Institutes of Health; Boston Scientific Corporation; Cleveland Clinic; National Heart, Lung, and Blood Institute; Alnylam Pharmaceuticals; Pfizer; Bristol-Myers Squibb","keywords":"Cardiac magnetic resonance; Cardiac amyloidosis; Magnetic resonance imaging; Transformer; Amyloidosis; Medicine; Cardiology; Internal medicine; Engineering; Radiology; Electrical engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006514034,0.0006284119,0.0009625512,0.0002498443,0.0001518356,0.0001768323,0.0003958006,0.0001490033,0.0000114757],"category_scores_gemma":[0.0003001987,0.0005554763,0.001784076,0.0005220958,0.0001365606,0.00006239955,0.000178996,0.0002440016,0.00003246892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001467988,"about_ca_system_score_gemma":0.0002486342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002484701,"about_ca_topic_score_gemma":0.000006342534,"domain_scores_codex":[0.9963633,0.0001863244,0.0005296508,0.001379155,0.0007626318,0.000778947],"domain_scores_gemma":[0.9977781,0.0002287029,0.0000739854,0.001451594,0.0002111164,0.0002564643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000197073,0.0001702137,0.03242253,0.0006128018,0.004048748,0.0001141937,0.001204821,0.01516433,0.2113807,0.00005399961,0.004518643,0.730112],"study_design_scores_gemma":[0.003117093,0.001006165,0.05346828,0.001838739,0.006251289,0.00009004815,0.001024798,0.009084242,0.6610572,0.0001026919,0.2597766,0.003182837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6439258,0.3286988,0.0218101,0.000812947,0.0007474713,0.002271123,0.0003580924,0.0001869337,0.00118871],"genre_scores_gemma":[0.9860064,0.008479963,0.003795125,0.0002339081,0.0003159441,0.0006763882,0.00009020213,0.0001889438,0.0002131656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7269291,"threshold_uncertainty_score":0.9996897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006911980164933713,"score_gpt":0.2443052014486091,"score_spread":0.2373932212836754,"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."}}