Consortium Leverages EHRs, Data Analytics for COVID-19 Research
The international consortium created a data analytics framework to aggregate information from EHRs and advance COVID-19 research.
Source: Getty Images
By Jessica Kent
- A consortium of research scientists has created a common data analytics model and shared framework that will aim to accelerate COVID-19 research by combining information from disparate EHRs internationally.
For more coronavirus updates, visit our resource page, updated twice daily by Xtelligent Healthcare Media.
The model, called the Consortium for Clinical Characterization of COVID-19 by EHR (4CE), offers clinicians and researchers a comprehensive tool to quickly discover trends and provide answers to questions about the virus.
The effort draws on clinical data from several sites, including the Perelman School of Medicine at the University of Pennsylvania. For future studies with 4CE, PennAI, a free machine learning tool developed at the Institute for Biomedical Informatics, will be available to each member site to power the project.
“We are excited to use our PennAI software for this project,” said paper co-author Jason Moore, PhD, the director of the Institute for Biomedical Informatics and a professor of Informatics. “It can be installed locally at each site and used to generate machine learning models for predicting COVID-19 outcomes such as death or disease severity. This is a critical need that we will contribute to the project.”
The consortium consists of 96 hospitals from around the world and has gathered data on more than 27,000 COVID-19 cases with 187,000 laboratory tests.
Previously, because of differences in EHRs, all of this data would not have been able to talk to each other in a way conducive to analysis. However, with so many sites putting their data into a common model and making it available to be processed and analyzed, scientists were able to detect new trends and patterns of the virus.
“For example, laboratory data were standardized from Penn Medicine's electronic health record to Logical Observation Identifiers, Names, and Codes (LOINC) and shared units of measure before analyzing their change over time. These steps were critical to uncovering initial clinical insights,” said Danielle Lee Mowry, PhD, Penn Medicine’s chief research information officer and an assistant professor of Informatics.
“Notable insights include abnormal trends in D-dimer protein, which is a measure of blood clotting, and C-reactive protein, a measure of inflammation, among COVID-19 patients.”
Among other insights were that liver functions initially presented as normal, but worsened over time as patients were hospitalized. White blood cell counts were also typically normal among patients but only elevated among those with the most serious forms of COVID-19.
“The COVID-19 data warehouse established at Penn Medicine will enable our researchers to access standardized data and generate results which can be replicated at sites around the world,” said John H. Holmes, PhD, IBI’s associate director for Medical Informatics and a professor of Informatics in Epidemiology.
“This opens the door to local insights about COVID-19 patients from the Philadelphia area while at the same time contributing to the global battle against this infectious disease.”
The results from the consortium add to the limited knowledge base of the virus, and demonstrates the potential for harmonized data extraction to study pandemics like COVID-19.
“At this early stage, we are partially blind to the underlying physiology of the disease and its interactions with different health system processes. The rapid collation of laboratory-level data across nearly 100 hospitals in five countries is novel in the questions it helps us ask,” consortium scientists stated.
“We are currently struggling to help public health agencies and hospitals better manage the epidemic. By identifying potential differences in care, with proxies of lab changes over time, numerous questions can be asked about whether certain clinical decisions may be affecting lab trajectories (and ultimately outcomes).”
While the consortium itself is new, it represents the culmination of years of work in healthcare data analytics.
“Our ability to rapidly respond to a global pandemic was made possible by years of institutional investments in health information technology and biomedical informatics expertise and infrastructure,” said Moore. “We are seeing the value of electronic health records and artificial intelligence in real-time.”
