{"id":"W4404528517","doi":"10.23889/ijpds.v9i1.2407","title":"Secondary use of routinely collected administrative health data for epidemiologic research: Answering research questions using data collected for a different purpose","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University; AIDS Vancouver","funders":"","keywords":"Data science; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04235104,0.0001497497,0.000383881,0.001283863,0.004376642,0.0003787348,0.003927568,0.0001430837,0.00005695351],"category_scores_gemma":[0.06946225,0.0001203323,0.0000425725,0.001335572,0.0003800323,0.004150196,0.001897895,0.001258404,0.000003130855],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125973,"about_ca_system_score_gemma":0.009368939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00146288,"about_ca_topic_score_gemma":0.001614269,"domain_scores_codex":[0.9934256,0.001166663,0.002044932,0.0008175721,0.001628742,0.0009164783],"domain_scores_gemma":[0.9786837,0.01402375,0.0008112534,0.001525328,0.00450219,0.0004538065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003446424,0.0005388604,0.01063616,0.004698489,0.0003297201,0.00001046136,0.005244431,0.0009403388,0.001641741,0.09661145,0.8113747,0.0645273],"study_design_scores_gemma":[0.0007687825,0.0003602091,0.01070227,0.001900735,0.0000158317,0.000021686,0.0007774686,0.8665441,0.00000746509,0.00529416,0.113493,0.000114273],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126835,0.0005721088,0.7507873,0.02467745,0.00889396,0.008614871,0.09353854,0.0001383639,0.00009393619],"genre_scores_gemma":[0.7960751,0.000564425,0.1436401,0.0007107657,0.002200359,0.0003425737,0.05548481,0.00005100225,0.0009309087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8656038,"threshold_uncertainty_score":0.9969195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9660910023644246,"score_gpt":0.746661212221578,"score_spread":0.2194297901428466,"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."}}