{"id":"W3215892644","doi":"10.37796/2211-8039.1302","title":"Comparison of Multiple Imputation Algorithms and Verification Using Whole-Genome Sequencing in the CMUH Genetic Biobank","year":2021,"lang":"en","type":"article","venue":"Biomedicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Medical University Hospital; National Applied Research Laboratories; Division of Materials Research; China Medical University; Taiwan Biobank","keywords":"Imputation (statistics); Biobank; Genome-wide association study; Data mining; Computer science; Single-nucleotide polymorphism; Genetic association; Missing data; Machine learning; Bioinformatics; Genetics; Biology","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":[0.0003323645,0.00007458219,0.0001613254,0.00005000444,0.00004617434,0.000005149977,0.00006745481,0.00009493113,0.000003234956],"category_scores_gemma":[0.0001956938,0.00005941428,0.00002356126,0.0001935803,0.0000841845,0.000001739941,0.00003177486,0.00004756504,8.281117e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002983415,"about_ca_system_score_gemma":0.00008428541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255223,"about_ca_topic_score_gemma":0.00004819364,"domain_scores_codex":[0.9991615,0.0001304547,0.0003034737,0.0001948766,0.0000824189,0.000127276],"domain_scores_gemma":[0.9995447,0.00003933401,0.0001343426,0.0001753987,0.00008128377,0.00002495428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000005134221,0.00002376052,0.1023578,0.00001481104,0.00001346685,0.000001495796,0.0004093513,0.0007012036,0.8937548,0.000003802167,0.00004821323,0.002666205],"study_design_scores_gemma":[0.0008435684,0.000229668,0.9393077,0.00002306503,0.00004157923,0.00004099235,0.002952008,0.03455813,0.01873594,0.00008397292,0.003057061,0.0001262344],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804324,0.003109824,0.01585464,0.000375386,0.00007584947,0.0001072945,0.00001851788,0.000002315341,0.00002380265],"genre_scores_gemma":[0.9893961,0.0001448268,0.009834465,0.0001400737,0.000115492,0.000005901428,0.0003429717,0.000006187372,0.00001401388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8750188,"threshold_uncertainty_score":0.2422844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04955184285685363,"score_gpt":0.3377828751287228,"score_spread":0.2882310322718692,"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."}}