{"id":"W2887643731","doi":"10.1016/j.cmpb.2018.07.014","title":"Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal","year":2018,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":106,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Atrial fibrillation; Support vector machine; Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Computer science; Paroxysmal atrial fibrillation; Feature selection; Curse of dimensionality; Machine learning; Cardiology; Medicine","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":[0.001099297,0.0001543171,0.000490709,0.000285158,0.00006352163,0.00001152211,0.00004049226,0.0001641314,0.000004119437],"category_scores_gemma":[0.00005988577,0.0001137836,0.0000783795,0.0005483195,0.000271781,0.00003118561,0.00002710309,0.0002054488,4.30999e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002285039,"about_ca_system_score_gemma":0.00002952583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005902043,"about_ca_topic_score_gemma":5.894419e-7,"domain_scores_codex":[0.9986432,0.0003482165,0.0003543232,0.0003021561,0.0002150801,0.0001370798],"domain_scores_gemma":[0.9992179,0.000191279,0.0002069593,0.0001567671,0.0001391126,0.00008804171],"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":[0.001175687,0.0001378753,0.1946778,0.0003788563,0.0001533781,0.000002633615,0.0008283486,0.0001079933,0.03993036,0.00002525,0.00001922289,0.7625626],"study_design_scores_gemma":[0.003226811,0.003961822,0.04201086,0.0006062774,0.0001775294,0.00001960993,0.00008876239,0.9467631,0.00195435,0.00002415128,0.001073052,0.00009367921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4661186,0.002238557,0.5301,0.0006614993,0.0003335789,0.0004667933,0.000006013567,0.00004909224,0.00002583029],"genre_scores_gemma":[0.6155446,0.00004461146,0.383274,0.0000183396,0.001013037,0.000002194051,0.00008515012,0.000009320939,0.000008772364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9466551,"threshold_uncertainty_score":0.4639962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1115635847067646,"score_gpt":0.3673926283905015,"score_spread":0.2558290436837369,"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."}}