{"id":"W4386355230","doi":"10.1101/2023.08.31.23294925","title":"Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Center for Long-Term Cybersecurity, University of California Berkeley; University of Sydney; Crohn's and Colitis Foundation of Canada","keywords":"Abnormality; Computer science; Generalization; Identification (biology); Enhanced Data Rates for GSM Evolution; Resource (disambiguation); Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Medicine; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006142316,0.0008555745,0.0007495104,0.0008046919,0.0002016711,0.0008350362,0.001293511,0.0009139242,0.001600647],"category_scores_gemma":[0.002960074,0.0002884626,0.0006190367,0.000616841,0.0003230106,0.0008092799,0.0005666353,0.000989724,0.0006712334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000561023,"about_ca_system_score_gemma":0.000575258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007560912,"about_ca_topic_score_gemma":0.006166192,"domain_scores_codex":[0.9997272,0.00005795419,0.00001703618,0.00008453873,0.00006607363,0.0000471828],"domain_scores_gemma":[0.9991053,0.0005443465,0.00006834591,0.00007927585,0.0001722362,0.00003052255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000412924,0.0001235361,0.002571982,0.0001122897,0.00007660971,0.0001623242,0.00005711782,0.8098502,0.008568703,0.002287775,0.003757499,0.172019],"study_design_scores_gemma":[0.000002946329,0.00001817206,0.0001977261,0.000003319367,0.000005942453,0.00001414894,0.000003368294,0.9984597,0.000614266,0.0004725436,0.0002050064,0.000002880134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1348387,0.002109843,0.8544931,0.0007324227,0.0001518801,0.0001053189,0.0007648075,0.003773741,0.003030136],"genre_scores_gemma":[0.8914575,0.0006823855,0.1012052,0.0003812196,0.0001220562,0.0001677581,0.001315134,0.0001923439,0.004476343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007560912,"threshold_uncertainty_score":0.01503378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0715977255041392,"score_gpt":0.3045120493612354,"score_spread":0.2329143238570962,"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."}}