{"id":"W3088576166","doi":"10.1109/access.2020.3025808","title":"Machine Learning-Based Automatic Detection of Central Sleep Apnea Events From a Pressure Sensitive Mat","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Carleton University; Bruyère; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; AGE-WELL","keywords":"Computer science; Artificial intelligence; Support vector machine; Deep learning; Machine learning; Hyperparameter; Polysomnography; Resampling; Sleep apnea; Apnea; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004057012,0.0006679036,0.0004511306,0.0005069052,0.0001687264,0.0003003674,0.0005190683,0.0004816655,0.0007368108],"category_scores_gemma":[0.001133072,0.0001761212,0.000377524,0.0002583126,0.0001458042,0.0003227034,0.0003753119,0.0003801037,0.0003803995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002351083,"about_ca_system_score_gemma":0.0003697819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003829403,"about_ca_topic_score_gemma":0.003998776,"domain_scores_codex":[0.999765,0.00003558019,0.00001752163,0.00008191622,0.00005941934,0.0000405197],"domain_scores_gemma":[0.9997122,0.0001042164,0.00003578985,0.00002714472,0.00008991759,0.00003075718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001399377,0.000974139,0.04835506,0.0002165696,0.0002890665,0.0006854107,0.0001086748,0.1161917,0.100452,0.0003899998,0.004475105,0.7264628],"study_design_scores_gemma":[0.00001554048,0.0001833081,0.01651439,0.00001060616,0.00002702367,0.0001628982,0.00001803861,0.9664286,0.01615499,0.0001321238,0.0003395151,0.00001295859],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.831697,0.001136544,0.1597094,0.000241009,0.0001842782,0.0001084915,0.0007169781,0.004107253,0.002098908],"genre_scores_gemma":[0.9682261,0.0001589799,0.02954432,0.00007113695,0.00002797483,0.00004654095,0.0007894877,0.00002760554,0.001107948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003829403,"threshold_uncertainty_score":0.007614195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02357675287039011,"score_gpt":0.2988203064533267,"score_spread":0.2752435535829366,"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."}}