{"id":"W1978884830","doi":"10.1016/j.jclinepi.2010.04.007","title":"Diabetics can be identified in an electronic medical record using laboratory tests and prescriptions","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"ca_institutions":"Public Health Ontario; Ottawa Hospital; Toronto Western Hospital; University of Toronto; University Health Network; Statistics Canada; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Medical prescription; Medical record; Electronic medical record; Diabetes mellitus; Family medicine; MEDLINE; Predictive value; Emergency medicine; Pediatrics; Internal medicine; Nursing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03302171,0.0001292771,0.00111013,0.0001858451,0.00007515852,0.00002628494,0.0009072757,0.0005304425,0.0000338542],"category_scores_gemma":[0.1120827,0.0001072345,0.0001179672,0.0002541552,0.000280109,0.0002842325,0.0001942262,0.004292592,0.000001293484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004159026,"about_ca_system_score_gemma":0.001381558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002213923,"about_ca_topic_score_gemma":0.004322839,"domain_scores_codex":[0.9895293,0.00630018,0.003020582,0.000357069,0.0002735221,0.0005193444],"domain_scores_gemma":[0.9782549,0.01825538,0.001768739,0.0005477567,0.000371593,0.0008016599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001864312,0.00009549771,0.9649062,0.00001519541,0.00001228675,0.00004581713,0.00007878018,0.00008511776,0.0001962502,0.0123705,0.0002132563,0.02196241],"study_design_scores_gemma":[0.0007645683,0.0007868529,0.8277281,0.00006026637,0.00001248893,0.0001875388,0.00001097135,0.1410483,0.000004604206,0.02469988,0.004561145,0.0001352716],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9536215,0.0002005192,0.01210601,0.03148796,0.002481878,0.00007066604,0.000001436516,0.00001862231,0.00001142057],"genre_scores_gemma":[0.9471494,0.0002672735,0.0462884,0.005410069,0.0008658271,0.000001545406,7.115222e-7,0.00001046161,0.000006304622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1409632,"threshold_uncertainty_score":0.9980046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1852224660473834,"score_gpt":0.5136758622002351,"score_spread":0.3284533961528517,"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."}}