{"id":"W4297491332","doi":"10.3389/fcvm.2022.998558","title":"Machine learning prediction of atrial fibrillation in cardiovascular patients using cardiac magnetic resonance and electronic health information","year":2022,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"Circle Cardiovascular Imaging; Alberta Innovates; Siemens Healthineers; Pfizer; Amgen","keywords":"Atrial fibrillation; Cardiology; Medicine; Internal medicine; Cardiac magnetic resonance; Magnetic resonance imaging; Cardiovascular health; Disease; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002986545,0.0001995073,0.001280063,0.0008490618,0.0001408693,0.000006951383,0.00006601064,0.00007327013,0.00001658111],"category_scores_gemma":[0.0002989081,0.0002024316,0.0006466247,0.0009789134,0.00007541107,0.0002483172,0.0001026381,0.0003775577,3.765864e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007674491,"about_ca_system_score_gemma":0.0001368473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009103541,"about_ca_topic_score_gemma":0.000003327528,"domain_scores_codex":[0.9967226,0.0006104399,0.0008178636,0.0003176133,0.001174685,0.0003568392],"domain_scores_gemma":[0.9992303,0.00003938036,0.0001977269,0.0003718557,0.00008365663,0.00007705601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003054576,0.000002673073,0.7714707,0.0001542073,0.0004297468,0.000002425876,0.0005982127,0.07315246,0.000002456718,0.00002187,0.00008978745,0.1537701],"study_design_scores_gemma":[0.009816264,0.000881523,0.7022197,0.0001462438,0.0006581489,0.00001022848,0.0008463633,0.04266012,0.000002738711,0.0000604021,0.242536,0.0001622772],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.3202373,0.6704119,0.004492107,0.000333367,0.0018357,0.002413431,0.00003911295,0.00005914966,0.0001779576],"genre_scores_gemma":[0.988749,0.009199386,0.0008578993,0.00004664476,0.0005804722,0.000008364147,0.0004905075,0.00002961059,0.00003805826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6685117,"threshold_uncertainty_score":0.8254921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443400043170206,"score_gpt":0.2427830939318296,"score_spread":0.2283490935001276,"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."}}