{"id":"W4388555293","doi":"10.48550/arxiv.2311.04229","title":"Exploring Best Practices for ECG Pre-Processing in Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Normalization (sociology); Computer science; Artificial intelligence; Machine learning; Signal processing; Sampling (signal processing); Pattern recognition (psychology); Data mining; Speech recognition; Digital signal processing; Filter (signal processing); Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004777432,0.0002729743,0.0005126975,0.0006101336,0.0001778011,0.00006106821,0.0002419738,0.0002032582,0.00001021706],"category_scores_gemma":[0.0006521747,0.0003073473,0.0002474984,0.0006584838,0.0000447623,0.0003078527,0.0003614565,0.001079606,0.00003453611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000241686,"about_ca_system_score_gemma":0.0001596826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002864155,"about_ca_topic_score_gemma":0.0003808055,"domain_scores_codex":[0.9983686,0.00007719921,0.0002487298,0.0008488532,0.00009933526,0.0003572997],"domain_scores_gemma":[0.9985862,0.0002035246,0.0005285912,0.000390048,0.0001541214,0.0001374969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005961925,0.0003385423,0.5841905,0.002630948,0.0003666656,0.0009994382,0.001125562,0.3875745,0.0003951475,0.0001359341,0.00002309616,0.02162345],"study_design_scores_gemma":[0.001547798,0.0002053894,0.008740704,0.00249283,0.001354916,0.000005756187,0.002719151,0.9792795,0.0003058917,0.0006680796,0.002130347,0.0005496894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846245,0.0003165746,0.01315035,0.0002368853,0.0003669038,0.0003358642,0.000009866028,0.0002868956,0.000672149],"genre_scores_gemma":[0.9758937,0.001634464,0.001026974,0.00001145868,0.0003425167,0.000009526126,0.00008149406,0.00006236774,0.02093744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.591705,"threshold_uncertainty_score":0.9999379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4916361074348901,"score_gpt":0.297468015869145,"score_spread":0.194168091565745,"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."}}