{"id":"W4386499052","doi":"10.36227/techrxiv.24078252","title":"A Multi-task Deep Learning Algorithm for Sleep Stage Scoring and Sleep Arousal Detection","year":2023,"lang":"en","type":"preprint","venue":"","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Sleep & Circadian Network","funders":"National Heart, Lung, and Blood Institute; National Science Foundation","keywords":"Polysomnography; Sleep (system call); Arousal; Interpretability; Artificial intelligence; Deep learning; Machine learning; Sleep Stages; Task (project management); Computer science; Cognitive psychology; Psychology; Electroencephalography; Psychiatry; Neuroscience; Engineering","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":[0.001276794,0.0009122381,0.0006486053,0.0005775677,0.0003533788,0.0005551063,0.001263277,0.001123437,0.001510726],"category_scores_gemma":[0.003126171,0.0003763863,0.0008418927,0.0006017903,0.0002695557,0.0007627699,0.001040717,0.001706295,0.000561676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007633261,"about_ca_system_score_gemma":0.00124508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008446058,"about_ca_topic_score_gemma":0.0107588,"domain_scores_codex":[0.9995759,0.0001075797,0.00003552196,0.0001300018,0.00008024283,0.00007081743],"domain_scores_gemma":[0.9994274,0.0002379121,0.00004486152,0.00005975849,0.0001922202,0.00003788431],"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":[0.0003272323,0.0004672409,0.005493129,0.0001109481,0.0001866082,0.0001539309,0.000118449,0.2595236,0.009934219,0.002693081,0.008939446,0.7120522],"study_design_scores_gemma":[0.00001057426,0.00004264773,0.0006322214,0.000007457594,0.00001039215,0.00001988798,0.000006005979,0.9965077,0.001146459,0.001154999,0.0004552688,0.000006419664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05186085,0.0008158058,0.9428751,0.0005379586,0.0001592052,0.0001303532,0.0004031209,0.001609659,0.001607862],"genre_scores_gemma":[0.6415539,0.0004242897,0.3489073,0.0006284389,0.0001149841,0.0004025255,0.001534171,0.0001397395,0.006294749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008446058,"threshold_uncertainty_score":0.01679379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05487129598313169,"score_gpt":0.3023144258615116,"score_spread":0.2474431298783799,"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."}}