The usefulness of administrative databases for identifying disease cohorts is increased with a multivariate model

Are allopurinol dose and duration of use nephroprotective in the elderly? A Medicare claims study of allopurinol use and incident renal failure

“…We used claims database definition of renal failure, which might lead to misclassification. However, this definition for renal failure has been shown to be valid previously40 and used commonly previously,41 42 though some studies have shown lower accuracy 43 44. Misclassification of incident renal failure can also occur due to variation in the length of the baseline period.…”

Applicability of Large Databases in Outcomes Research

“…For example, the sensitivity of a diagnostic code for a kidney disease has increased from 38% to 80% by applying a multivariate model with several patient and hospitalization variables. 41 Clinicians and researchers should take the responsibility of active participation in designing and improvising future administrative databases to accomplish goals beyond reimbursements. 42 A need for providers (for instance, hospitals and surgeons) to develop a central database exists.…”

Improving Patient Cohort Identification Using Natural Language Processing

“…Several studies have investigated the accuracy of structured administrative data such as the World Health Organization's (WHO) International Classification of Diseases, Ninth Revision (ICD-9) billing codes when identifying patient cohorts [3][4][5][6][7][8][9][10][11]. Extracting structured information using ICD-9 codes has been shown to have good recall, precision, and specificity [3,4] when identifying distinct patient populations.…”