{"id":"W3089738630","doi":"10.1016/j.cjca.2020.07.161","title":"MACHINE LEARNING FOR LEFT VENTRICULAR SEGMENTATION AND SCAR QUANTIFICATION IN HYPERTROPHIC CARDIOMYOPATHY PATIENTS","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Cardiomyopathy and Myosin Studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Medicine; Hypertrophic cardiomyopathy; Ventricle; Cardiac magnetic resonance; Cardiology; Internal medicine; Magnetic resonance imaging; Segmentation; Clinical Practice; Cardiac magnetic resonance imaging; Hypertrophic scar; Radiology; Artificial intelligence; Pathology; Physical therapy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001838951,0.0003702514,0.0006403563,0.001170658,0.0003476556,0.0009292667,0.0005026567,0.0007970948,0.00143855],"category_scores_gemma":[0.004151204,0.0002006836,0.0005362595,0.0004326715,0.0002041987,0.0003741855,0.0004697384,0.0007787618,0.0003794043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004212447,"about_ca_system_score_gemma":0.0005688767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003642441,"about_ca_topic_score_gemma":0.004394535,"domain_scores_codex":[0.9995947,0.0001609882,0.00003951522,0.00007943997,0.00006400615,0.00006123782],"domain_scores_gemma":[0.9984931,0.001020588,0.0001160524,0.00007499893,0.0002020407,0.00009329797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002854817,0.0008461429,0.3083569,0.0001989022,0.000393194,0.0004956328,0.0002554863,0.05735085,0.01303245,0.001171142,0.005701315,0.6093432],"study_design_scores_gemma":[0.00007234933,0.0004599999,0.1132193,0.00007008052,0.0001248247,0.0005077638,0.0002036198,0.8777269,0.004703851,0.001907868,0.0009693786,0.00003406227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9235688,0.002333516,0.0695697,0.0008948589,0.0001074107,0.00009787107,0.0009210223,0.0004737136,0.002033213],"genre_scores_gemma":[0.9832579,0.0002745635,0.01494451,0.0000755224,0.00005195264,0.00003817436,0.0006601923,0.00002733759,0.0006698081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003642441,"threshold_uncertainty_score":0.009725451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0215542519146797,"score_gpt":0.2405202473016637,"score_spread":0.218965995386984,"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."}}