{"id":"W3118737132","doi":"10.1016/j.bspc.2021.102992","title":"DeepFilter: An ECG baseline wander removal filter using deep learning techniques","year":2021,"lang":"en","type":"preprint","venue":"Biomedical Signal Processing and Control","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Ericsson (Canada)","funders":"","keywords":"Noise (video); Similarity (geometry); Computer science; Deep learning; Filter (signal processing); Artificial intelligence; Ambulatory; Noise reduction; Baseline (sea); Code (set theory); Mean squared error; Pattern recognition (psychology); Speech recognition; Statistics; Medicine; Mathematics; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000381681,0.0007399709,0.000514961,0.0004038721,0.0002376944,0.0005355924,0.0007211418,0.0009872147,0.004739022],"category_scores_gemma":[0.000752873,0.0003768659,0.000549886,0.0003625965,0.000179841,0.0005604249,0.0008728008,0.001177484,0.001789001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000333876,"about_ca_system_score_gemma":0.0007576643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005522019,"about_ca_topic_score_gemma":0.01186417,"domain_scores_codex":[0.9998602,0.0000125578,0.000006375331,0.00002861801,0.00007090568,0.00002142601],"domain_scores_gemma":[0.9998375,0.0000561157,0.00001058866,0.00002688512,0.00005305277,0.00001585225],"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":[0.0002662242,0.0001513491,0.0008077901,0.0001142892,0.0001719133,0.0001530809,0.00004153052,0.04573301,0.05720172,0.004109709,0.0184215,0.8728278],"study_design_scores_gemma":[0.00004461348,0.000115623,0.001220968,0.00002173388,0.00005804484,0.0001891703,0.0000104112,0.9380583,0.04269433,0.003869656,0.01369045,0.00002671485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006241158,0.0002900432,0.9893301,0.0001221394,0.00009938217,0.00002219676,0.0002726976,0.002835347,0.0007869679],"genre_scores_gemma":[0.1546738,0.000750056,0.8136659,0.0005706938,0.0001582962,0.00009699116,0.001964316,0.0008061354,0.02731401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005522019,"threshold_uncertainty_score":0.01585358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02186719057408919,"score_gpt":0.2990972641070069,"score_spread":0.2772300735329177,"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."}}