{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001156993,0.0002397814,0.0003197105,0.000139019,0.0000965771,0.0006502532,0.002007886,0.0001983036,0.00001590156],"category_scores_gemma":[0.001851536,0.0002524122,0.00005743886,0.0002374123,0.00002770881,0.0006804696,0.002998322,0.0008987651,0.00001237233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006493532,"about_ca_system_score_gemma":0.0008802782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003220035,"about_ca_topic_score_gemma":0.0001910809,"domain_scores_codex":[0.9971548,0.0003870266,0.0005264139,0.001214481,0.0003671024,0.0003502105],"domain_scores_gemma":[0.9971032,0.0008951204,0.0003350801,0.001432602,0.0001004355,0.0001335924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006263448,0.0003642359,0.6375358,0.00565999,0.0002448084,0.0004105608,0.00630226,0.01689821,0.0001575627,0.109012,0.01137062,0.2119814],"study_design_scores_gemma":[0.000186397,0.00004764966,0.03764306,0.0002014761,0.00002795207,0.000005083816,0.00005735454,0.9231317,0.0000311973,0.03413539,0.004266031,0.0002667232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009183438,0.0004605178,0.9330738,0.05542992,0.0008143327,0.0006859496,0.00003098973,0.0002155346,0.0001055681],"genre_scores_gemma":[0.6227467,0.00004363602,0.3762808,0.000370051,0.0001926804,0.0001647931,0.0001761801,0.00002212442,0.000003049894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9062335,"threshold_uncertainty_score":0.9999928,"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."}}