Validation of a Delirium Risk Assessment Using Electronic Medical Record Information.

Rudolph JL, Doherty K, Kelly B, Driver JA, Archambault E. Validation of a Delirium Risk Assessment Using Electronic Medical Record Information. Journal of The American Medical Directors Association. 2016 Mar 1; 17(3):244-8.

Dimensions for VA is a web-based tool available to VA staff that enables detailed searches of published research and research projects.

If you have VA-Intranet access, click here for more information vaww.hsrd.research.va.gov/dimensions/

VA staff not currently on the VA network can access Dimensions by registering for an account using their VA email address.    Search Dimensions for VA for this citation
* Don't have VA-internal network access or a VA email address? Try searching the free-to-the-public version of Dimensions

Search for Abstract from PubMed

---

Abstract:

OBJECTIVE: Identifying patients at risk for delirium allows prompt application of prevention, diagnostic, and treatment strategies; but is rarely done. Once delirium develops, patients are more likely to need posthospitalization skilled care. This study developed an a priori electronic prediction rule using independent risk factors identified in a National Center of Clinical Excellence meta-analysis and validated the ability to predict delirium in 2 cohorts. DESIGN: Retrospective analysis followed by prospective validation. SETTING: Tertiary VA Hospital in New England. PARTICIPANTS: A total of 27,625 medical records of hospitalized patients and 246 prospectively enrolled patients admitted to the hospital. MEASUREMENTS: The electronic delirium risk prediction rule was created using data obtained from the patient electronic medical record (EMR). The primary outcome, delirium, was identified 2 ways: (1) from the EMR (retrospective cohort) and (2) clinical assessment on enrollment and daily thereafter (prospective participants). We assessed discrimination of the delirium prediction rule with the C-statistic. Secondary outcomes were length of stay and discharge to rehabilitation. RESULTS: Retrospectively, delirium was identified in 8% of medical records (n = 2343); prospectively, delirium during hospitalization was present in 26% of participants (n = 64). In the retrospective cohort, medical record delirium was identified in 2%, 3%, 11%, and 38% of the low, intermediate, high, and very high-risk groups, respectively (C-statistic = 0.81; 95% confidence interval 0.80-0.82). Prospectively, the electronic prediction rule identified delirium in 15%, 18%, 31%, and 55% of these groups (C-statistic = 0.69; 95% confidence interval 0.61-0.77). Compared with low-risk patients, those at high- or very high delirium risk had increased length of stay (5.7 5.6 vs 3.7 2.7 days; P = .001) and higher rates of discharge to rehabilitation (8.9% vs 20.8%; P = .02). CONCLUSIONS: Automatic calculation of delirium risk using an EMR algorithm identifies patients at risk for delirium, which creates a critical opportunity for gaining clinical efficiencies and improving delirium identification, including those needing skilled care.