{"id":"W2111589117","doi":"10.1186/1471-2288-14-36","title":"Evaluating bias due to data linkage error in electronic healthcare records","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Hospital for Sick Children; Intensive Care Society; Medical Research Council; National Institute for Health and Care Research; NHS Health Scotland","keywords":"Identifier; Record linkage; Linkage (software); Gold standard (test); Word error rate; Computer science; Imputation (statistics); Statistics; Probabilistic logic; Data mining; Missing data; Data set; Standard error; Medicine; Artificial intelligence; Mathematics; Population","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6394793,0.0001669629,0.0008231283,0.001223558,0.0002291421,0.0001526727,0.006863059,0.0003222363,0.003293406],"category_scores_gemma":[0.8603182,0.0001244588,0.00006607333,0.002723577,0.0004164986,0.0002635641,0.006126467,0.001798008,0.001672955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001880298,"about_ca_system_score_gemma":0.00263265,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004369332,"about_ca_topic_score_gemma":0.09030966,"domain_scores_codex":[0.734938,0.241934,0.002698733,0.003115046,0.01421232,0.003101878],"domain_scores_gemma":[0.4539711,0.5336879,0.0004000413,0.00838872,0.001272805,0.002279496],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002331347,0.00008126542,0.001267249,0.00007418097,0.000009832858,0.00003397545,0.0004587799,0.00002069424,0.00003207957,0.03850866,0.04115869,0.9181215],"study_design_scores_gemma":[0.001343295,0.00187176,0.01666641,0.000199945,0.000008734478,0.00003048684,0.003200525,0.09765793,0.00005937495,0.4002251,0.4784217,0.0003148067],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0874657,0.0004607928,0.8524637,0.0551026,0.0008368647,0.0009685638,0.00004354091,0.00005200067,0.002606248],"genre_scores_gemma":[0.2782663,0.0004027736,0.6975009,0.01615244,0.001625307,0.0003770727,0.0002761832,0.0000640272,0.005335028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9178067,"threshold_uncertainty_score":0.9991044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9728506852504919,"score_gpt":0.764426510343351,"score_spread":0.2084241749071409,"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."}}