Estimating risk factors for patients with potential drug-related problems using electronic pharmacy data

OBJECTIVE: To validate a computer-based program to identify patients at hig h risk for drug-related problems. DESIGN: Computerized analysis of pharmacy dispensing records and manual rev iew of medical records. SETTING: Ambulatory clinics at a Veterans Affairs Medical Center. PATIENTS: 246 randomly selected patients who were receiving at least one ou tpatient medication in the previous 24 months. MAIN OUTCOME MEASURES: Presence of six previously established criteria rega rding medication use. These criteria are five or more medications, greater than or equal to 12 doses per day, four or more changes to the medication r egimen, three or more chronic diseases, history of noncompliance, and prese nce of a drug requiring therapeutic drug monitoring (TDM). RESULTS: Spearman rho rank order correlation coefficients ranged from 0.63 to 0.91 for criteria pertaining to the number of medications, daily doses, changes in the medication regimen, and number of chronic diseases (all sign ificant, p = 0.0001). The computer program underestimated the number of chr onic diseases and overestimated the number of daily doses. The level of agr eement between the computer program and chart review for patient noncomplia nce was low (Kappa = 0.38), with the computer more likely to indicate a pat ient was noncompliant. A high level of agreement was seen between the compu ter program and chart review for the presence of a drug requiring TDM (Kapp a = 0.83). For all six criteria, the computer program had a sensitivity of 65.7% and specificity of 88.2%. CONCLUSIONS: When compared with medical records, the use of this program to evaluate electronic pharmacy data can be efficient to screen large numbers of patients who may be at high risk for drug-related problems. This method may be useful for clinical pharmacists in providing pharmaceutical service s to patients who are most likely to benefit.