Format

Send to

Choose Destination
Clin Epidemiol. 2018 Oct 16;10:1509-1521. doi: 10.2147/CLEP.S160764. eCollection 2018.

A phenotyping algorithm to identify acute ischemic stroke accurately from a national biobank: the Million Veteran Program.

Author information

1
Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Cooperative Studies Program, VA Boston Healthcare System, Boston, MA, USA, Kelly.Cho@va.gov.
2
Department of Medicine, Cardiology Section, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA.
3
Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA.
4
Department of Medicine, Division of Aging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA, Kelly.Cho@va.gov.
5
Department of Neurology, Baltimore VA Medical Center and University of Maryland School of Medicine, Baltimore, MD, USA.
6
Harvard T. H. Chan School of Public Health, Boston, MA, USA.
7
Atlanta VA Medical Center, Decatur, GA, USA.
8
Department of Medicine, Division of Cardiovascular Disease, Emory University School of Medicine, Atlanta, GA, USA.

Abstract

Background:

Large databases provide an efficient way to analyze patient data. A challenge with these databases is the inconsistency of ICD codes and a potential for inaccurate ascertainment of cases. The purpose of this study was to develop and validate a reliable protocol to identify cases of acute ischemic stroke (AIS) from a large national database.

Methods:

Using the national Veterans Affairs electronic health-record system, Center for Medicare and Medicaid Services, and National Death Index data, we developed an algorithm to identify cases of AIS. Using a combination of inpatient and outpatient ICD9 codes, we selected cases of AIS and controls from 1992 to 2014. Diagnoses determined after medical-chart review were considered the gold standard. We used a machine-learning algorithm and a neural network approach to identify AIS from ICD9 codes and electronic health-record information and compared it with a previous rule-based stroke-classification algorithm.

Results:

We reviewed administrative hospital data, ICD9 codes, and medical records of 268 patients in detail. Compared with the gold standard, this AIS algorithm had a sensitivity of 91%, specificity of 95%, and positive predictive value of 88%. A total of 80,508 highly likely cases of AIS were identified using the algorithm in the Veterans Affairs national cardiovascular disease-risk cohort (n=2,114,458).

Conclusion:

Our algorithm had high specificity for identifying AIS in a nationwide electronic health-record system. This approach may be utilized in other electronic health databases to accurately identify patients with AIS.

KEYWORDS:

acute ischemic stroke; administrative health data; algorithm; big data; cerebrovascular accident; large databases

Supplemental Content

Full text links

Icon for Dove Medical Press Icon for PubMed Central
Loading ...
Support Center