{"id":"W4387949114","doi":"10.1109/jbhi.2023.3327470","title":"Towards Real-Time Sleep Stage Prediction and Online Calibration Based on Architecturally Switchable Deep Learning Models","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Sleep (system call); Sleep Stages; Artificial intelligence; Robustness (evolution); Deep learning; Machine learning; Polysomnography; Electroencephalography; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004129278,0.001177319,0.0004854001,0.0004293112,0.0002172134,0.0005326074,0.001187813,0.0005592071,0.001151631],"category_scores_gemma":[0.001324276,0.000431202,0.0004522314,0.0003702237,0.0002923453,0.001019611,0.0008116424,0.001099248,0.0004615192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004579445,"about_ca_system_score_gemma":0.0007167544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006646258,"about_ca_topic_score_gemma":0.01259268,"domain_scores_codex":[0.9998056,0.00002909752,0.000009769649,0.00008525487,0.00003310124,0.00003716264],"domain_scores_gemma":[0.9998036,0.00006706488,0.00002826464,0.0000288948,0.00005416607,0.00001814575],"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":[0.0004761437,0.0003194968,0.01208443,0.0001743186,0.0001921355,0.000247223,0.0001879554,0.3820737,0.03005379,0.00368536,0.008323491,0.5621819],"study_design_scores_gemma":[0.000008558803,0.00003704887,0.0009679987,0.00001097972,0.00001787107,0.00002501827,0.00001416785,0.9939892,0.002746136,0.001541143,0.0006338871,0.000007968587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1407799,0.001861414,0.8472933,0.0004194427,0.0002045368,0.0001016003,0.0007067854,0.004856518,0.003776563],"genre_scores_gemma":[0.8967566,0.000545145,0.09637973,0.0003344118,0.00008191414,0.0001674336,0.001233547,0.0001430379,0.004358143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006646258,"threshold_uncertainty_score":0.01321512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05215935783271644,"score_gpt":0.3068296070184289,"score_spread":0.2546702491857125,"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."}}