A group of researchers and scientists from across the globe, including some at Penn Medicine, are pooling electronic health record data to help discover trends relating to the spread of COVID-19.
The Consortium for Clinical Characterization of COVID-19 consists of 96 hospitals around the world and has gathered data on more than 27,000 COVID-19 cases and 187,000 laboratory test results, according to Penn Medicine News. 4CE takes the global COVID-19 patient data and combines all the results to create aggregate health records which scientists can then use to answer patient questions as well as work to prevent further spread.
For future studies in partnership with 4CE, PennAI, a machine learning tool developed at Penn's Institute for Biomedical Informatics, will be available to each member of the project. PennAI uses artificial intelligence to create large numbers of analyses with different variables and methods to predict outcomes
Director of the Institute of Biomedical Informatics Jason Moore told Penn Medicine News that PennAI can "generate machine learning models for predicting COVID-19 outcomes such as death or disease severity.”
4CE has found that among COVID-19 patients, liver condition can worsen over time and white blood cell counts may be elevated in patients infected with severe forms of COVID-19.
“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," Moore said. “We are seeing the value of electronic health records and artificial intelligence in real-time.”
In addition to collaborating with the international consortium, Penn researchers have also contributed to the COVID-19 effort through the development of COBALT, a mental health platform that provides support for healthcare workers, and COVID Watch, a text message-based platform that checks on patients recovering from COVID-19 at home.
All comments eligible for publication in Daily Pennsylvanian, Inc. publications.