{"id":"W4390485420","doi":"10.1109/sipaim56729.2023.10373478","title":"Generative Data by β-Variational Autoencoders Help Build Stronger Classifiers: ECG Use Case","year":2023,"lang":"en","type":"article","venue":"","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Normal Sinus Rhythm; Artificial intelligence; Computer science; Medical diagnosis; Pattern recognition (psychology); Abnormality; Machine learning; Autoencoder; Generative grammar; Generative model; Deep learning; Atrial fibrillation; Medicine; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002389797,0.0001297959,0.0001998235,0.0001307078,0.0001426207,0.00007169171,0.0001164041,0.00007965338,0.0004083318],"category_scores_gemma":[0.0002212617,0.0001049634,0.0000605602,0.0004221093,0.00004334401,0.0002747397,0.0001152394,0.0001670767,0.0001878234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005977447,"about_ca_system_score_gemma":0.0001047218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008029826,"about_ca_topic_score_gemma":0.0000827116,"domain_scores_codex":[0.9987966,0.00004633586,0.0002047585,0.0004052996,0.0003040913,0.0002429498],"domain_scores_gemma":[0.9989312,0.000148052,0.00004710704,0.0006190645,0.0000896105,0.0001649326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003857619,0.0001762107,0.06149527,0.00002678854,0.0008578128,0.001810858,0.0003039572,0.0010634,0.004410499,0.0003151063,0.9243433,0.005158166],"study_design_scores_gemma":[0.001061749,0.00009384324,0.003352506,0.00003444571,0.0004362947,0.0002057274,0.002409439,0.9589906,0.001025602,0.00004085789,0.03208384,0.0002650807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7537379,0.0003152847,0.2044119,0.03114711,0.001463803,0.0006513339,0.001851588,0.001525343,0.00489569],"genre_scores_gemma":[0.7658294,0.0001354399,0.07812349,0.001154418,0.001469192,0.00003270281,0.005585698,0.00006475391,0.1476049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9579272,"threshold_uncertainty_score":0.4470947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1293727377658139,"score_gpt":0.3555843784581408,"score_spread":0.2262116406923269,"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."}}