{"id":"W3043668670","doi":"10.1101/2020.07.13.20146118","title":"Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; BioClinica; F. Hoffmann-La Roche; University of Southern California; Biogen; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Missing data; Imputation (statistics); Computer science; Data mining; Dementia; Ground truth; Test data; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03006045,0.0009691045,0.002009015,0.00212716,0.0009907032,0.002774945,0.004637208,0.002656764,0.003889517],"category_scores_gemma":[0.09024716,0.001000896,0.001680991,0.002344937,0.001521057,0.002742004,0.003773296,0.004369502,0.001073341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001266555,"about_ca_system_score_gemma":0.003244496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003597766,"about_ca_topic_score_gemma":0.002956507,"domain_scores_codex":[0.9860453,0.01087355,0.0006739617,0.001064348,0.001008565,0.000334195],"domain_scores_gemma":[0.9376298,0.05125053,0.002231255,0.003895419,0.004232917,0.0007601891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001068091,0.0003620131,0.01283701,0.0005434577,0.0004970345,0.000626017,0.0007669575,0.6780314,0.00153677,0.06787368,0.007437895,0.2284197],"study_design_scores_gemma":[0.00005962117,0.00006304744,0.000647374,0.0000941063,0.00003134049,0.0001076466,0.00009339765,0.9148312,0.001099642,0.08156817,0.001379345,0.00002505043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009003146,0.000323196,0.9882479,0.001266289,0.00005977853,0.000115035,0.0001377617,0.0003687493,0.0004780821],"genre_scores_gemma":[0.2997837,0.0002981334,0.6972218,0.000542137,0.0001581932,0.0004199845,0.0005606468,0.0001217827,0.0008936871],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03006045,"threshold_uncertainty_score":0.1589768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2679946980452029,"score_gpt":0.4283008900316649,"score_spread":0.160306191986462,"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."}}