{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002266396,0.0001725157,0.0002096022,0.0001927641,0.002100465,0.0001390515,0.001777704,0.00001696177,0.00001135332],"category_scores_gemma":[0.000202171,0.0001696422,0.0000684424,0.0007323604,0.0001177481,0.0006638202,0.0008649858,0.0003649961,0.000002281403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002774619,"about_ca_system_score_gemma":0.000625462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002186242,"about_ca_topic_score_gemma":0.000008517003,"domain_scores_codex":[0.9968442,0.000356439,0.0002937354,0.0009916947,0.0008761183,0.0006378343],"domain_scores_gemma":[0.9981719,0.0004776642,0.0002344819,0.0008545261,0.00005267674,0.0002087683],"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":[0.00002621303,0.000133533,0.0005915409,0.00009262821,0.000005875535,0.000004294985,0.005395441,0.5723672,0.00001326251,0.1733142,0.00331207,0.2447437],"study_design_scores_gemma":[0.0001448274,0.0008219712,0.0006210472,0.00003508687,0.000001415566,0.00001767979,0.000207613,0.9760832,0.00003434423,0.01761525,0.004253093,0.0001644686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002637379,0.000369522,0.9841214,0.01007286,0.0007196731,0.0006650956,0.00007455598,0.0002687824,0.001070661],"genre_scores_gemma":[0.7876184,0.00001179592,0.208254,0.003465862,0.0001424544,0.0003376707,0.00003360372,0.00001762258,0.000118658],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.784981,"threshold_uncertainty_score":0.9991987,"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."}}