{"id":"W4223923854","doi":"10.1093/gigascience/giac013","title":"Benchmarking missing-values approaches for predictive models on health databases","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Museo delle Scienze; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Missing data; Imputation (statistics); Benchmarking; Computer science; Predictive modelling; Machine learning; Discriminative model; Data mining; Benchmark (surveying); Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02782867,0.001517688,0.001594238,0.002490866,0.0009516436,0.002652042,0.004364253,0.002377074,0.002878137],"category_scores_gemma":[0.08834396,0.0006778245,0.001705172,0.00408661,0.001236488,0.003974447,0.003051735,0.003134516,0.001240705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002200355,"about_ca_system_score_gemma":0.002574795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009391876,"about_ca_topic_score_gemma":0.006874867,"domain_scores_codex":[0.9859913,0.008726422,0.0009970615,0.001843443,0.002024905,0.0004168524],"domain_scores_gemma":[0.9377002,0.04859568,0.001684338,0.007709788,0.003524668,0.0007853138],"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":[0.0006995433,0.0003581479,0.01215818,0.0007452408,0.0005811892,0.0001340449,0.0002152055,0.8614689,0.0003189688,0.01132957,0.01017159,0.1018195],"study_design_scores_gemma":[0.00006991914,0.0000819929,0.001029275,0.00008988367,0.00004224297,0.00004413515,0.00006421797,0.9779233,0.0006352186,0.01848675,0.001517767,0.00001533347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2129063,0.01076768,0.7384586,0.006780862,0.000682288,0.0006193604,0.01017721,0.01292112,0.006686666],"genre_scores_gemma":[0.645411,0.002144805,0.3362346,0.0007711127,0.0002144376,0.0005833075,0.01317664,0.0005757006,0.0008884879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02782867,"threshold_uncertainty_score":0.1471738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1635602176719167,"score_gpt":0.3428177368146273,"score_spread":0.1792575191427107,"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."}}