Search

OBJECTIVES: Developing scalable strategies for the early identification of Alzheimer's disease and related dementia (ADRD) is important. We aimed to develop a passive digital signature for early identification of ADRD using electronic medical record (EMR) data. DESIGN: A case‐control study. SETTING: The Indiana Network for Patient Care (INPC), a regional health information exchange in Indiana. PARTICIPANTS: Patients identified with ADRD and matched controls. MEASUREMENTS: We used data from the INPC that includes structured and unstructured (visit notes, progress notes, medication notes) EMR data. Cases and controls were matched on age, race, and sex. The derivation sample consisted of 10 504 cases and 39 510 controls; the validation sample included 4500 cases and 16 952 controls. We constructed models to identify early 1‐ to 10‐year, 3‐ to 10‐year, and 5‐ to 10‐year ADRD signatures. The analyses included 14 diagnostic risk variables and 10 drug classes in addition to new variables produced from unstructured data (eg, disorientation, confusion, wandering, apraxia, etc). The area under the receiver operating characteristics (AUROC) curve was used to determine the best models. RESULTS: The AUROC curves for the validation samples for the 1‐ to 10‐year, 3‐ to 10‐year, and 5‐ to 10‐year models that used only structured data were.689,.649, and.633, respectively. For the same samples and years, models that used both structured and unstructured data produced AUROC curves of.798,.748, and.704, respectively. Using a cutoff to maximize sensitivity and specificity, the 1‐ to 10‐year, 3‐ to 10‐year, and 5‐ to 10‐year models had sensitivity that ranged from 51% to 62% and specificity that ranged from 80% to 89%. CONCLUSION: EMR‐based data provide a targeted and scalable process for early identification of risk of ADRD as an alternative to traditional population screening. J Am Geriatr Soc 68:511–518, 2020 [ABSTRACT FROM AUTHOR]

This article describes how key aspects of the Sandra Eskenazi Center for Brain Care Innovation's (SECBCI) care model can inform other entities on the development of new models of population health management, through a framework that emphasizes social, behavioral, and environmental determinants of health, as well as biomedical aspects. The SECBCI is a collaboration with Eskenazi Health and community-based organizations such as the Central Indiana Council on Aging Area Agency on Aging and the Greater Indianapolis Chapter of the Alzheimer's Association in Central Indiana. [ABSTRACT FROM AUTHOR]

Background: Central line-associated bloodstream infections (CLABSIs) are among the most common hospital-acquired infections and can lead to increased patient morbidity and mortality rates. Implementation of practice guidelines and recommended prevention bundles has historically been suboptimal, suggesting that improvements in implementation methods could further reductions in CLABSI rates. In this article, we describe the agile implementation methodology and present details of how it was successfully used to reduce CLABSI., Methods: We conducted an observational study of patients with central line catheters at 2 adult tertiary care hospitals in Indianapolis from January 2015 to June 2017., Results: The intervention successfully reduced the CLABSI rate from 1.76 infections per 1,000 central line days to 1.24 (rate ratio = 0.70; P = .011). We also observed reductions in the rates of Clostridium difficile and surgical site infections, whereas catheter-associated urinary tract infections remained stable., Conclusions: Using the AI model, we were able to successfully implement evidence-based practices to reduce the rate of CLABSIs at our facility., (Copyright © 2018 Association for Professionals in Infection Control and Epidemiology, Inc. Published by Elsevier Inc. All rights reserved.)