Mayo Clinic, Rochester, MN
Copyright 2016, American College of Chest Physicians. All Rights Reserved.
SESSION TITLE: Pulmonary Vascular Disease: VTE
SESSION TYPE: Original Investigation Poster
PRESENTED ON: Saturday, April 16, 2016 at 11:45 AM - 12:45 PM
PURPOSE: The simplified pulmonary embolism severity index (sPESI) is a well validated tool for risk stratification of patients with pulmonary embolism (PE). A PE patient is classified as ‘high risk’ based on the presence of any of the following variables: Age > 80; history of cancer; history of chronic cardiopulmonary disease; heart rate ≥ 110; systolic BP < 100mmHg or oxygen saturation < 90% at time of PE diagnosis. We aimed to develop and validate an automated search algorithm (Strategy) to retrospectively identify patients with ‘high risk’ PE by analyzing the electronic medical record (EMR)
METHODS: A random sample of 200 PE patients was selected from an electronic database of confirmed PE cases for the purpose of creating a derivation (n=100) and validation (n=100) cohort. Calculation of the sPESI by manual chart review was considered as the gold standard. We created an electronic automated sPESI search algorithm through sequential steps using keywords applied to an institutional EMR data base. The sPESI search algorithm was developed and refined in the initial cohort of 100 patients (derivation cohort). We then applied the final sPESI search algorithm to the validation cohort (n=100) to assess reliability and validity. Sensitivity and specificity of the automated sPESI algorithm to identify ‘high risk’ PE was determined by comparing to the ‘gold standard’ (manual sPESI score ≥1)
RESULTS: The initial search strategy in the derivation cohort showed a sensitivity and specificity of 96% and 92% respectively for the identification of ‘high risk’ PE. After refinements in the search algorithm, we were able to achieve a higher sensitivity and a similar specificity at 98.7% and 92%, respectively. This final electronic sPESI search algorithm was then applied to the validation cohort and again yielded excellent sensitivity and specificity of 97.6% and 100% respectively for the identification of ‘high risk’ PE
CONCLUSIONS: We have developed an electronic sPESI algorithm that identifies ‘high risk’ PE with a very high degree of accuracy in compare to the gold standard
CLINICAL IMPLICATIONS: This tool is an excellent alternative to manual chart review for the calculation of sPESI scores in retrospective research projects and future studies. Further validation of this tool in other EMR environments will establish external reliability and validity
DISCLOSURE: The following authors have nothing to disclose: Bashar Alkinj, Bibek Pannu, Melissa Passe, Vivek Iyer, Rahul Kashyap
No Product/Research Disclosure Information
Become a CHEST member and receive a FREE subscription as a benefit of membership.
Individuals can purchase this article on ScienceDirect.
Individuals can purchase a subscription to the journal.
Individuals can purchase a subscription to the journal or buy individual articles.
Learn more about membership or Purchase a Full Subscription.
Institutional access is now available through ScienceDirect and can be purchased at myelsevier.com.
Some tools below are only available to our subscribers or users with an online account.
Download citation file:
Web of Science® Times Cited:
Customize your page view by dragging & repositioning the boxes below.
Enter your username and email address. We'll send you a reminder to the email address on record.
Athens and Shibboleth are access management services that provide single sign-on to protected resources. They replace the multiple user names and passwords necessary to access subscription-based content with a single user name and password that can be entered once per session. It operates independently of a user's location or IP address. If your institution uses Athens or Shibboleth authentication, please contact your site administrator to receive your user name and password.