Early Recognition of Undiagnosed Viral Syndromes and Their Predictors Over Time
Abstract
This proposal addresses the area of Emerging Viral Diseases by using computational methods to identify unusual viral syndromes before they spread significantly. Central Critical Problem: While some methods to rapidly identify emerging viral diseases require a large increase in cases, the COVID-19 pandemic has made it clear that emerging diseases must be detected more quickly. Most surveillance systems were late in identification, detecting an increase only after the virus was well entrenched. Improved systems would not necessarily require knowing what to look for ahead of time, or always waiting for a large increase of cases. Earlier recognition of COVID-19 could have facilitated early containment and eradication efforts. Such recognition requires a capability to identify distinctive features in clinical presentation and which of these are related. In this proposal, we will apply computational methods to electronic health record (EHR) data to find unusual viral syndromes, cluster them, and characterize them over time. These methods will enable more rapid biosurveillance for present and future needs. Overview: Accelerated biosurveillance systems benefit Service Members, Veterans, and the entire nation as there still exist opportunities to better utilize data contained in the EHR. While many methods use public data, these data sources do not contain the level of clinical detail present in the health record, nor do they come from clinicians trained to diagnose patients. More rapid biosurveillance may be possible by better understanding what clinicians document as concerning. In our work on COVID-19, we note that clinicians record distinctive features (e.g., travel from Hubei) and findings which may involve escalation (e.g., with public health authorities). While more such examples exist, there remain opportunities to listen to observant clinicians to catch emerging threats earlier. To translate clinical findings in the EHR to biosurveillance requires identifying distinctive features, distinctive cases, and determining whether cases share common features. Aim 1 of this proposal will identify distinctive features (i.e., flags) in EHR data such as exposures, risk factors, and expression of concern for possible emerging viral disease. Aim 2 will link these distinctive cases and features such that diseases with common causes can be identified within small case numbers. Aim 3 will characterize concepts of viral disease over time to provide more timely and detailed information about the disease than what can be found in publicly available reports. This approach will help to understand potential new disease and enhance this understanding over time. Applicability and Impact: As demonstrated by COVID-19, emerging viral diseases represent a major threat to U.S. Veterans and Service Members, the nation, and the world. These viruses compromise their health, economic stability, well-being, and in the case of Service Members, their combat readiness. Our proposal will be conducted in the Department of Veterans Affairs EHR since it contains more detailed data on more individuals over time than almost any other resource as well as being most likely to benefit Service Members than perhaps any other dataset. The proposed approach will permit earlier containment, earlier eradication, and improved care in the face of emerging viral disease.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Dec 28, 2022
- Source ID
- W81XWH2210950
Entities
People
- Makoto Jones
Organizations
- George E. Wahlen Department of VA Medical Center
- United States Army