{"id":"W3160047223","doi":"10.1161/circ.142.suppl_3.16082","title":"Abstract 16082: Machine Learning to Improve Left Ventricular Scar Quantification in Hypertrophic Cardiomyopathy Patients","year":2020,"lang":"en","type":"article","venue":"Circulation","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"","keywords":"Hypertrophic cardiomyopathy; Artificial intelligence; Medicine; Convolutional neural network; Deep learning; Segmentation; Magnetic resonance imaging; Robustness (evolution); Sørensen–Dice coefficient; Ventricle; Image segmentation; Pattern recognition (psychology); Computer science; Machine learning; Radiology; Cardiology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001145971,0.0004839796,0.0004585521,0.0005290814,0.0001391049,0.000474019,0.0004256461,0.0006222219,0.001331488],"category_scores_gemma":[0.002605052,0.0001375392,0.0003667173,0.000260422,0.0001739912,0.0003108848,0.0004096137,0.000397308,0.0003372753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000407923,"about_ca_system_score_gemma":0.0004777792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001743463,"about_ca_topic_score_gemma":0.002006615,"domain_scores_codex":[0.9997576,0.00008043586,0.00002297576,0.00006935613,0.00004240537,0.00002714756],"domain_scores_gemma":[0.9994107,0.0002487773,0.00008628506,0.00005987323,0.0001421641,0.00005225674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001401016,0.0007953444,0.2484783,0.000299925,0.0003072059,0.0006139813,0.0001687944,0.1663166,0.02833606,0.0006885394,0.007557298,0.545037],"study_design_scores_gemma":[0.0000495572,0.0005960531,0.05900289,0.00005619896,0.00007142814,0.0003129311,0.00003269795,0.9307676,0.00728664,0.0007131754,0.001089057,0.00002177688],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9251136,0.001583193,0.06947691,0.0007101229,0.0001057327,0.0001134091,0.0008013442,0.0006167132,0.00147903],"genre_scores_gemma":[0.9762725,0.0002090106,0.02154227,0.0001419669,0.00005961678,0.00007107187,0.0009122724,0.00003139146,0.0007599943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001743463,"threshold_uncertainty_score":0.006060541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0153716726166461,"score_gpt":0.2444060055673082,"score_spread":0.2290343329506621,"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."}}