{"id":"W3198546327","doi":"10.3389/fcvm.2021.669860","title":"Deep Learning Analysis of Echocardiographic Images to Predict Positive Genotype in Patients With Hypertrophic Cardiomyopathy","year":2021,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Cardiomyopathy and Myosin Studies","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; American Heart Association; Korea Institute of Oriental Medicine; National Institute on Aging; Irving Medical Center, Columbia University; Feldstein Medical Foundation","keywords":"Hypertrophic cardiomyopathy; Parasternal line; Receiver operating characteristic; Medicine; Internal medicine; Cardiology; Genotype; Predictive value; Nomogram; Cutoff; Artificial intelligence; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001254751,0.0004116652,0.003473484,0.002613302,0.00007501418,0.000009363862,0.0001431351,0.0001677382,0.00001175246],"category_scores_gemma":[0.0005870786,0.0003403426,0.001448852,0.007404224,0.000302337,0.00009065193,0.0001319711,0.0005350721,0.000001402617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002627499,"about_ca_system_score_gemma":0.0001041494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002536203,"about_ca_topic_score_gemma":0.00003065185,"domain_scores_codex":[0.9959812,0.0004901019,0.0006824276,0.0008867678,0.001399968,0.0005595388],"domain_scores_gemma":[0.9978086,0.00008319577,0.0001108119,0.0009882612,0.0007710364,0.0002380516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008171753,0.0001232288,0.9343429,0.0001195161,0.02357119,0.001056742,0.001233642,0.02098019,0.00006748914,0.000002813779,0.0001972405,0.01748792],"study_design_scores_gemma":[0.006333487,0.0007372478,0.9734201,0.0005369347,0.01505986,0.00003201545,0.002080484,0.0002463901,0.0001418749,0.000007848599,0.001094844,0.0003089125],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8471463,0.1143693,0.03428108,0.0002343068,0.0007135331,0.001048471,0.00003332859,0.0000605729,0.002113079],"genre_scores_gemma":[0.9944416,0.001622465,0.003173339,0.000165092,0.0001914637,0.00007050519,0.0002392141,0.00005435016,0.00004199563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1472952,"threshold_uncertainty_score":0.9999049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004220205913108017,"score_gpt":0.202020093482652,"score_spread":0.197799887569544,"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."}}