{"id":"W3159624973","doi":"10.1186/s12859-021-04138-z","title":"Dynamic model updating (DMU) approach for statistical learning model building with missing data","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Missing data; Categorical variable; Data mining; Imputation (statistics); Computer science; Cluster analysis; Closeness; Statistical model; Bayesian probability; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001014674,0.0003016519,0.0005017215,0.00007035703,0.0003611585,0.0002847689,0.0004537122,0.0001392029,0.00001626118],"category_scores_gemma":[0.005032705,0.0002505443,0.00005152196,0.0002105055,0.0001141543,0.0004547028,0.0003551122,0.0003925141,0.000002701463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007123276,"about_ca_system_score_gemma":0.0005057483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001717067,"about_ca_topic_score_gemma":0.000004958796,"domain_scores_codex":[0.9977346,0.00008546229,0.0007996161,0.0003971361,0.0004241906,0.0005590086],"domain_scores_gemma":[0.9963557,0.002093291,0.0003204677,0.0008123824,0.0002329842,0.0001851559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006807009,0.0001536263,0.00009587442,0.003355715,0.0000726996,0.000004740206,0.0007716661,0.08280791,0.0001397432,0.8622508,0.0005962886,0.04968287],"study_design_scores_gemma":[0.0004584854,0.0000358667,0.000004339378,0.0001311411,0.0001216731,0.00003245389,0.0006928246,0.7759144,0.00003268019,0.2222559,0.00001698994,0.0003032132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001464579,0.00002006203,0.995313,0.00003496603,0.00002841521,0.0003442962,0.0005476524,0.000136523,0.003428587],"genre_scores_gemma":[0.002366871,0.000006285388,0.9967127,0.00008746246,0.00002413877,0.00002813479,0.0005887627,0.00005960828,0.0001260227],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6931065,"threshold_uncertainty_score":0.9999947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1479590701890201,"score_gpt":0.3960589705597026,"score_spread":0.2480999003706826,"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."}}