{"id":"W4411343702","doi":"10.3390/brainsci15060639","title":"Bridging the Gap: Missing Data Imputation Methods and Their Effect on Dementia Classification Performance","year":2025,"lang":"en","type":"article","venue":"Brain Sciences","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Bridging (networking); Imputation (statistics); Missing data; Dementia; Computer science; Data mining; Psychology; Artificial intelligence; Machine learning; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005084726,0.00007150625,0.00008594819,0.0001230262,0.0005022573,0.0001547296,0.0002186896,0.00001748126,0.00001436627],"category_scores_gemma":[0.0006368627,0.00003781612,0.00001567162,0.0004475221,0.0003074433,0.0001986942,0.0001239286,0.00009075923,0.000003662284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001401609,"about_ca_system_score_gemma":0.0001028009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007862738,"about_ca_topic_score_gemma":0.000001372227,"domain_scores_codex":[0.9989015,0.0002921541,0.000114205,0.0003017233,0.0002192437,0.0001711374],"domain_scores_gemma":[0.9988903,0.0007752259,0.00004066427,0.0002224132,0.00003837836,0.00003295572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002560403,0.00001682336,0.06366815,0.00004289719,0.00002221524,3.283215e-7,0.00009866283,0.000001467822,0.01779342,0.0002761958,0.0007120526,0.9173422],"study_design_scores_gemma":[0.0004255514,0.0004255136,0.7820834,0.000194269,0.00004428882,0.000006764026,0.0003986236,0.183978,0.0293769,0.0003331985,0.002677434,0.00005610837],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9247438,0.0006197664,0.04446053,0.01817291,0.00009812522,0.0004459305,0.000001844135,0.0000262155,0.01143086],"genre_scores_gemma":[0.9966286,0.00003311492,0.001830079,0.001161953,0.00003560665,0.00001397683,0.00001211925,0.000002420585,0.0002820698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9172861,"threshold_uncertainty_score":0.3863008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1000815930345847,"score_gpt":0.4639385331354082,"score_spread":0.3638569401008235,"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."}}