{"id":"W2906777138","doi":"10.1093/jamia/ocy164","title":"Enrichment sampling for a multi-site patient survey using electronic health records and census data","year":2018,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Human Genome Research Institute; Canada Excellence Research Chairs, Government of Canada; National Heart, Lung, and Blood Institute; Cincinnati Children's Hospital Medical Center; Children's Hospital of Philadelphia","keywords":"Census; Sampling frame; Stratified sampling; Sampling (signal processing); Sampling design; Sample size determination; Demography; Ethnic group; Sample (material); Survey data collection; American Community Survey; Medicine; Survey sampling; Geography; Health equity; Gerontology; Statistics; Environmental health; Computer science; Public health; Population; Mathematics; Political science; Sociology; Pathology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07585823,0.00006885388,0.0002872952,0.00006841261,0.0005410461,0.00004054734,0.0003724043,0.00006109948,0.000005832806],"category_scores_gemma":[0.06723764,0.00004906279,0.00005097689,0.00032608,0.0002506688,0.0002012004,0.0001226364,0.0002991437,7.207842e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006854543,"about_ca_system_score_gemma":0.001357449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002276796,"about_ca_topic_score_gemma":0.003505817,"domain_scores_codex":[0.9924344,0.005695133,0.0007105227,0.00006241746,0.0007389437,0.0003585352],"domain_scores_gemma":[0.989106,0.007401708,0.002741531,0.00015886,0.0004170048,0.0001748976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003767584,0.0003550838,0.5720012,0.00004871231,0.0006905894,0.000001051428,0.07715844,0.00004301165,0.00005792996,0.0002072761,0.01779286,0.3278763],"study_design_scores_gemma":[0.002459936,0.002113893,0.8445231,0.0002423086,0.0001557107,0.00003703857,0.01888204,0.05416022,0.00004170682,0.0005012876,0.07648434,0.0003984016],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473357,0.00008671201,0.04936911,0.002211376,0.0007373482,0.0001746934,0.00006818509,0.000005493228,0.00001141095],"genre_scores_gemma":[0.8599781,0.001115502,0.1314929,0.006527869,0.0007788157,0.000002636371,0.00003285921,0.00001495821,0.00005643241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3274779,"threshold_uncertainty_score":0.9515984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3533000150091042,"score_gpt":0.5169291976826397,"score_spread":0.1636291826735355,"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."}}