{"id":"W4389036121","doi":"10.23889/ijpds.v8i1.2176","title":"Generating synthetic data from administrative health records for drug safety and effectiveness studies","year":2023,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Manitoba Health; McGill University; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Real world data; Population; Medical prescription; Computer science; Medicine; Data science; Pharmacology; Environmental health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005590062,0.0001300584,0.0002418183,0.0001984724,0.0006558919,0.0002671932,0.001629657,0.00002417051,0.000006260763],"category_scores_gemma":[0.01236689,0.0001115563,0.00002357276,0.0002212379,0.0001673589,0.002600687,0.0008747869,0.000118475,0.000001364802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002328311,"about_ca_system_score_gemma":0.000220743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007823215,"about_ca_topic_score_gemma":0.0003011735,"domain_scores_codex":[0.9980444,0.0001003668,0.0005399996,0.0005567698,0.0005259798,0.0002324906],"domain_scores_gemma":[0.995033,0.003146146,0.0005009106,0.0005968378,0.000630289,0.00009284207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002102211,0.0004566848,0.02251437,0.0007788154,0.001258915,0.00004020255,0.005841257,0.002047665,0.01179438,0.3871595,0.07305709,0.4929489],"study_design_scores_gemma":[0.0008291127,0.0001861938,0.00859043,0.0008108617,0.00004217279,0.00005320103,0.001284532,0.3330964,0.0008897458,0.6500956,0.003778361,0.0003433649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1598019,0.000232343,0.823782,0.003126469,0.002617036,0.001150037,0.009062573,0.0002085725,0.00001908516],"genre_scores_gemma":[0.6228616,0.0006085171,0.3729516,0.000141642,0.0005569172,0.00005280998,0.002721267,0.00002772067,0.00007788577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4926056,"threshold_uncertainty_score":0.9959524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5555152502297888,"score_gpt":0.5974494260819023,"score_spread":0.04193417585211356,"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."}}