Bjornsen, Susan S.

Background. Annual foot examinations (FE) constitute a critical component of care for diabetes. Documented evidence of FE is central to quality-of-care reporting; however, manual abstraction of electronic medical records (EMR) is slow, expensive, and subject to error. The objective of this study was to test the hypothesis that text mining of the EMR results in ascertaining FE evidence with accuracy comparable to manual abstraction. Methods. The text of inpatient and outpatient clinical reports was searched with natural-language (NL) queries for evidence of neurological, vascular, and structural components of FE. A manual medical records audit was used for validation. The reference standard consisted of 3 independent sets used for development (n=200 ), validation (n=118 ), and reliability (n=80 ). Results. The reliability of manual auditing was 91% (95% confidence interval [CI]= 85— 97) and was determined by comparing the results of an additional audit to the original audit using the records in the reliability set. The accuracy of the NL query requiring 1 of 3 FE components was 89% (95% CI= 83— 95). The accuracy of the query requiring any 2 of 3 components was 88% (95% CI= 82— 94). The accuracy of the query requiring all 3 components was 75% (95% CI= 68— 83). Conclusions. The free text of the EMR is a viable source of information necessary for quality of health care reporting on the evidence of FE for patients with diabetes. The low-cost methodology is scalable to monitoring large numbers of patients and can be used to streamline quality-of-care reporting.

OBJECTIVE—The Mayo Health System Diabetes Translation Project sought to assess models of community-based diabetes care and use of a diabetes electronic management system (DEMS). Planned care is a redesigned model of chronic disease care that involves guideline implementation, support of self-management, and use of clinical information systems. RESEARCH DESIGN AND METHODS—We studied adult diabetic patients attending three primary care practice sites in Wisconsin and Minnesota. We implemented planned care at all sites and DEMS in the practice of 16 primary care providers. We assessed quality of diabetes care using standard indicators for 200 patients randomly selected from each site at baseline and at 24 months of implementation. We used multivariable analyses to estimate the association between planned care and DEMS and each quality indicator. RESULTS—Planned care was associated with improvements in measurement of HbA1c (odds ratio 7.0 [95% CI 4.2–11.6]), HDL cholesterol (5.6 [4.1–7.5]), and microalbuminuria (5.3 [3.5–8.0]), as well as the provision of tobacco advice (6.9 [4.7–10.1]), among other performance measures. DEMS use was associated with improvements in all indicators, including microalbuminuria (3.2 [1.9–5.2]), retinal examination (2.4 [1.5–3.9]), foot examinations (2.3 [1.2–4.4]), and self-management support (2.6 [1.7–3.8]). Although planned care was associated with improvements in metabolic control, we observed no additional metabolic benefit when providers used DEMS. CONCLUSIONS—Planned care was associated with improved performance and metabolic outcomes in primary care. DEMS use augmented the impact of planned care on performance outcomes but not on metabolic outcomes. Optimal identification of the best translation of evidence to diabetes practice will require longer follow-up or new care-delivery models.