{"id":"W4224250841","doi":"10.1093/ehjdh/ztac004","title":"Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis","year":2022,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Technische Universität München","keywords":"Cardiology; Internal medicine; Medicine; Stenosis; Aortic valve stenosis; Aortic valve; Hazard ratio; Confidence interval","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":[],"consensus_categories":[],"category_scores_codex":[0.0002955928,0.000186564,0.0003545079,0.00006856483,0.0006708796,0.0000904321,0.00006560983,0.0000195394,0.00004021033],"category_scores_gemma":[0.00007436609,0.000129088,0.0003702519,0.0002065054,0.00008342831,0.0002895956,0.00004128515,0.0004037711,0.000001241198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004968569,"about_ca_system_score_gemma":0.0002907494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009667882,"about_ca_topic_score_gemma":0.000006509686,"domain_scores_codex":[0.9981703,0.0002749898,0.0004445534,0.0002336398,0.0005248118,0.0003517023],"domain_scores_gemma":[0.9989646,0.0002035489,0.0003071088,0.0001623876,0.0001614355,0.0002008903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003323634,0.0005914217,0.9717737,0.0001083994,0.000275173,0.000008791363,0.0005308962,0.001369951,0.000002436378,0.000003078864,0.001393699,0.02061878],"study_design_scores_gemma":[0.003646445,0.001236478,0.9916901,0.0002330757,0.0001661949,0.00004508111,0.001169794,0.001416763,7.388782e-7,0.00004018348,0.0002399855,0.0001151318],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960284,0.0005232443,0.0001627501,0.0009701878,0.0003898561,0.0009925325,0.0008405464,0.00002563459,0.00006680096],"genre_scores_gemma":[0.998252,0.00001137576,0.0001519795,0.0003595025,0.0003300747,0.00003292653,0.0006997061,0.00004191355,0.0001205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02050365,"threshold_uncertainty_score":0.5264057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02370293776615857,"score_gpt":0.3027257709217228,"score_spread":0.2790228331555642,"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."}}