{"id":"W4308636435","doi":"10.1002/pds.5566","title":"High‐dimensional propensity scores for empirical covariate selection in secondary database studies: Planning, implementation, and reporting","year":2022,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; International Society for Pharmacoepidemiology","keywords":"Covariate; Medicine; Propensity score matching; Pharmacoepidemiology; Selection (genetic algorithm); Statistics; Econometrics; Internal medicine; Pharmacology; Computer science; Machine learning","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":["metaresearch"],"category_scores_codex":[0.5616139,0.003076012,0.004377186,0.01558441,0.002707343,0.01412263,0.007683247,0.005572178,0.009543431],"category_scores_gemma":[0.8067768,0.003938021,0.004771011,0.02281525,0.006866759,0.01097463,0.01307918,0.01046125,0.004796129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005278474,"about_ca_system_score_gemma":0.02521442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003266108,"about_ca_topic_score_gemma":0.002883682,"domain_scores_codex":[0.3357508,0.5060833,0.1048283,0.008085216,0.04397419,0.001278254],"domain_scores_gemma":[0.1265927,0.604529,0.08101193,0.1245451,0.0609984,0.002322794],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007334634,0.0002091114,0.01297988,0.0124391,0.001656241,0.0003172305,0.003097753,0.01205819,0.0006843046,0.2131518,0.1273386,0.6153344],"study_design_scores_gemma":[0.001887126,0.0008765704,0.01177014,0.02326196,0.001231178,0.0009319273,0.001527592,0.07253629,0.00766819,0.5882328,0.2894926,0.0005836103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001185588,0.00191292,0.9673689,0.009481747,0.0006917848,0.01202804,0.003081847,0.001470812,0.002778431],"genre_scores_gemma":[0.01325104,0.002844244,0.9517855,0.001653129,0.0007509174,0.02713941,0.001822483,0.0003216189,0.0004315895],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4383861,"threshold_uncertainty_score":0.5406082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.44729527161018,"score_gpt":0.5604829685782081,"score_spread":0.1131876969680281,"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."}}