{"id":"W3171841570","doi":"10.21203/rs.3.rs-1005999/v1","title":"Hypertrophic Cardiomyopathy Diagnosis Based on Cardiovascular Magnetic Resonance Using Deep Learning Techniques","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Cardiomyopathy and Myosin Studies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hypertrophic cardiomyopathy; Artificial intelligence; Convolutional neural network; Deep learning; Magnetic resonance imaging; Computer science; Pattern recognition (psychology); Cardiac magnetic resonance; Medicine; Radiology; Cardiology","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003695254,0.0006913495,0.002067731,0.001109951,0.0007234949,0.0002627602,0.0003787474,0.0007447652,0.0001090813],"category_scores_gemma":[0.002619912,0.0006686721,0.002351844,0.001234713,0.0004531393,0.00006635642,0.001575865,0.004502248,0.00002564276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091843,"about_ca_system_score_gemma":0.0008787084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008185339,"about_ca_topic_score_gemma":0.00001401747,"domain_scores_codex":[0.9907387,0.002156374,0.0005703053,0.001773056,0.003491323,0.001270203],"domain_scores_gemma":[0.9944393,0.0007170108,0.00008923839,0.002420058,0.001953654,0.0003807245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001315313,0.001068394,0.2010216,0.01313563,0.002013924,0.02184368,0.001858123,0.0162492,0.001786448,0.00004396592,0.000941027,0.7387227],"study_design_scores_gemma":[0.00628704,0.007238743,0.2314445,0.05996194,0.004943831,0.001026953,0.008012136,0.02765844,0.02805195,0.0001976946,0.6207917,0.004385132],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.4861841,0.5005908,0.001292166,0.0005777763,0.0006002911,0.003973778,0.00007618669,0.0006093976,0.00609544],"genre_scores_gemma":[0.9559049,0.03514671,0.004575689,0.0001304999,0.001540855,0.002114699,0.0001474327,0.000212647,0.0002265513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7343376,"threshold_uncertainty_score":0.9995764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06119767099353544,"score_gpt":0.3531503059506409,"score_spread":0.2919526349571054,"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."}}