{"id":"W4205665932","doi":"10.17504/protocols.io.b3nfqmbn","title":"Benchmarking missing-values approaches for predictive models on health databases v2","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Missing data; Imputation (statistics); Benchmarking; Computer science; Predictive modelling; Machine learning; Discriminative model; Benchmark (surveying); Artificial intelligence; Data mining; Random forest","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03624053,0.001764722,0.00213663,0.002728777,0.0009862741,0.003407679,0.004743862,0.002982653,0.005140421],"category_scores_gemma":[0.1021198,0.000919509,0.002267448,0.004382368,0.001233703,0.003479376,0.003336782,0.003401091,0.002200611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002425547,"about_ca_system_score_gemma":0.003617604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01387276,"about_ca_topic_score_gemma":0.01026957,"domain_scores_codex":[0.980418,0.01241657,0.001424685,0.002228596,0.002853145,0.0006589725],"domain_scores_gemma":[0.9252825,0.06002001,0.001720146,0.008343205,0.003787219,0.0008468907],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001089667,0.0004415521,0.01149862,0.001192429,0.0008675705,0.0001703922,0.0002373132,0.8293363,0.0003271339,0.01511257,0.01884374,0.1208827],"study_design_scores_gemma":[0.0001137099,0.0001256682,0.001106493,0.0001461994,0.00005889709,0.00006014471,0.00006035063,0.974004,0.0006648308,0.02072349,0.002913539,0.00002260681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1365409,0.01304837,0.791732,0.006961018,0.0009654434,0.001028746,0.01825131,0.02173928,0.009733023],"genre_scores_gemma":[0.562034,0.002747602,0.4071395,0.0009025215,0.0003070318,0.0008192742,0.02329977,0.001237187,0.001513144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9637595,"threshold_uncertainty_score":0.1916605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2279906903560777,"score_gpt":0.3799372270832587,"score_spread":0.1519465367271809,"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."}}