{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01743342,0.0006720418,0.001270549,0.001158659,0.000425696,0.0008349065,0.002109437,0.001463649,0.001924939],"category_scores_gemma":[0.04149969,0.0005823094,0.001058312,0.001493951,0.0006086401,0.002044912,0.001549088,0.002056426,0.0004183436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008235823,"about_ca_system_score_gemma":0.001617728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003261288,"about_ca_topic_score_gemma":0.002026423,"domain_scores_codex":[0.9963273,0.002404128,0.0002189284,0.0004268108,0.0004689446,0.0001538938],"domain_scores_gemma":[0.9587408,0.03536687,0.00117307,0.001652475,0.002796198,0.0002705032],"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":[0.0003350461,0.0005232815,0.01824006,0.0002619622,0.0002622009,0.0001045253,0.0003716635,0.5483502,0.00110792,0.0143383,0.00197283,0.4141319],"study_design_scores_gemma":[0.00001637494,0.00005884983,0.0005486606,0.00002226352,0.00001304757,0.00003869295,0.00001799702,0.997027,0.0003962806,0.001530102,0.000326172,0.000004545661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02464239,0.0007270055,0.9733733,0.0002429819,0.00002110494,0.0001256895,0.00003105343,0.0003808555,0.000455591],"genre_scores_gemma":[0.1993377,0.0006930243,0.7980725,0.0001334973,0.00005999559,0.0003830349,0.0002375491,0.0001157423,0.0009669808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01743342,"threshold_uncertainty_score":0.09219784,"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."}}