{"id":"W3206855610","doi":"10.2196/30824","title":"Self–Training With Quantile Errors for Multivariate Missing Data Imputation for Regression Problems in Electronic Medical Records: Algorithm Development Study","year":2021,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; Ministry of Food and Drug Safety; Korea Medical Device Development Fund","keywords":"Missing data; Imputation (statistics); Wilcoxon signed-rank test; Decision tree; Computer science; Statistics; Random forest; Multivariate statistics; Test data; Mean squared error; Data mining; Artificial intelligence; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009547148,0.0002534017,0.0006232081,0.0001652018,0.00135919,0.00004607651,0.0003071217,0.0002560439,0.00002416654],"category_scores_gemma":[0.002707231,0.0002073446,0.00002302642,0.0005528781,0.00003925375,0.0003069443,0.0001771472,0.0007303003,0.000003080887],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005421871,"about_ca_system_score_gemma":0.01951515,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008736441,"about_ca_topic_score_gemma":0.04707498,"domain_scores_codex":[0.9940084,0.001473947,0.001435928,0.0009645791,0.0004949202,0.001622192],"domain_scores_gemma":[0.9955021,0.002149146,0.0005372791,0.0004955757,0.0006063349,0.0007095918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001419519,0.0004302367,0.3081402,0.002038937,0.00003673877,0.000007294324,0.05309329,0.000006398184,0.000001482656,0.0002217756,0.0005443021,0.6353374],"study_design_scores_gemma":[0.005257851,0.001968466,0.06046415,0.00167539,0.000003370157,0.00002480614,0.1220653,0.5212282,0.000003448093,0.0008030244,0.2856092,0.0008968981],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6406247,0.00416883,0.279905,0.04987761,0.001549431,0.0229904,0.000247352,0.000535833,0.0001008213],"genre_scores_gemma":[0.9153838,0.0003880539,0.07545064,0.002353897,0.0004151216,0.004229367,0.001541669,0.0001006487,0.0001368595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6344404,"threshold_uncertainty_score":0.9999409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2461216845613886,"score_gpt":0.4960280886115006,"score_spread":0.249906404050112,"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."}}