{"id":"W4410029919","doi":"10.1016/j.artmed.2025.103152","title":"Multi-modal signal integration for enhanced sleep stage classification: Leveraging EOG and 2-channel EEG data with advanced feature extraction","year":2025,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Feature extraction; Electroencephalography; Pattern recognition (psychology); Artificial intelligence; Modal; Electrooculography; Channel (broadcasting); SIGNAL (programming language); Feature (linguistics); Sleep Stages; Speech recognition; Sleep (system call); Eye movement; Polysomnography; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005141057,0.0002166427,0.0002666888,0.0002517659,0.0001979658,0.00007643008,0.0004326666,0.00009610734,0.00002483308],"category_scores_gemma":[0.0007433771,0.0001664399,0.00001872535,0.0005264826,0.0002870957,0.0005767786,0.0000835027,0.0003545738,0.000003575499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006072385,"about_ca_system_score_gemma":0.00005134913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005704137,"about_ca_topic_score_gemma":0.0004262714,"domain_scores_codex":[0.9981185,0.00009317835,0.0004434205,0.0008274184,0.0002347665,0.0002826941],"domain_scores_gemma":[0.9985765,0.0006677012,0.0001651721,0.0004126987,0.0001165172,0.00006144698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003703836,0.00009565988,0.00002996485,0.00004321321,0.000005745651,0.000005898708,0.001492441,0.00173404,0.7482781,0.002757954,0.00009733018,0.2450893],"study_design_scores_gemma":[0.0002041071,0.0002326905,0.000342791,0.0003419056,0.00001372375,0.000004977202,0.003797218,0.4929307,0.4997974,0.001759959,0.0004309108,0.0001435342],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1513043,0.0001360349,0.8422073,0.004834776,0.0005699146,0.0006570531,0.00001803537,0.00006417895,0.0002083716],"genre_scores_gemma":[0.9899869,0.00007680595,0.008573708,0.0007031595,0.0001282545,0.0000704421,0.00004380311,0.00001400747,0.0004029401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8386826,"threshold_uncertainty_score":0.6787224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1237726440257612,"score_gpt":0.3903782848849525,"score_spread":0.2666056408591913,"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."}}