{"id":"W4408557388","doi":"10.1177/13872877251327754","title":"EEG biomarkers for Alzheimer's disease: A novel automated pipeline for detecting and monitoring disease progression","year":2025,"lang":"en","type":"article","venue":"Journal of Alzheimer s Disease","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Electroencephalography; Artificial intelligence; Computer science; Pipeline (software); Machine learning; Dementia; Preprocessor; Disease; Random forest; Pattern recognition (psychology); Population; Feature extraction; Medicine; Neuroscience; Psychology; Pathology","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":[0.001265094,0.001843772,0.0009000276,0.002724805,0.0005216634,0.001460194,0.001060545,0.0007760178,0.00359718],"category_scores_gemma":[0.003030476,0.0004581166,0.000888902,0.001171161,0.0002855563,0.0008798736,0.001080165,0.000911033,0.002623483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004653961,"about_ca_system_score_gemma":0.001215704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003984739,"about_ca_topic_score_gemma":0.006967856,"domain_scores_codex":[0.9992025,0.0001186884,0.0000628276,0.0002637531,0.0002668805,0.00008528408],"domain_scores_gemma":[0.9988312,0.0002781427,0.0001486288,0.0001225393,0.0005534034,0.00006604628],"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":[0.0006824229,0.0005780171,0.02240164,0.0002784163,0.0002158134,0.00044722,0.0002126195,0.01290957,0.09796924,0.001180309,0.01203283,0.851092],"study_design_scores_gemma":[0.0002448729,0.0009310234,0.08324288,0.0001142607,0.000266915,0.001736199,0.0002144653,0.7560129,0.1249154,0.008936933,0.02319222,0.0001920152],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07326322,0.001034528,0.9017028,0.0005431109,0.000113076,0.0007306488,0.003238091,0.01745023,0.001924257],"genre_scores_gemma":[0.2696423,0.0007189891,0.7175933,0.0002259145,0.0001415527,0.0009462474,0.005762815,0.000422764,0.004546122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003984739,"threshold_uncertainty_score":0.01203376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04545921971397161,"score_gpt":0.3538632408138105,"score_spread":0.3084040210998389,"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."}}