SAN FRANCISCO, April 06, 2022 (GLOBE NEWSWIRE) -- Vir Biotechnology, Inc. (Nasdaq: VIR) today announced that a team of three company scientists were named one of the winners of the Pediatric COVID-19 Data Challenge, sponsored by the Biomedical Advanced Research and Development Authority (BARDA) and the U.S. Department of Health and Human Services (HHS). The challenge asked participants to develop, train and validate computational models that could help healthcare providers predict which of their pediatric patients with COVID-19 were likely to develop severe complications. The dataset comprised of de-identified electronic health records data available through the National COVID Cohort Collaborative (N3C) Data Enclave. The N3C is a harmonized data repository of records from more than 116,000 pediatric outpatients from across the United States.
The contributing scientists were Istvan Bartha, Ph.D., M.S., a senior scientist at Humabs Biomed, a subsidiary of Vir; Cyrus Maher, Ph.D., MPH, M.S., director of machine learning at Vir; and Amalio Telenti, M.D., Ph.D., chief data scientist and senior vice president of bioinformatics at Vir.
Responding to the challenge, the Vir team employed a state-of-the-art machine learning model called the “missingness-aware gradient boosted tree classifier,” which assessed the risk of hospitalization and severe outcomes among pediatric patients by extracting patterns in both the data that were present and the observations that were absent.
“The tremendous volume of data generated during the pandemic provides significant opportunities for the development and implementation of predictive tools that can help anticipate critical care needs, optimize treatment for the highest risk patients and reduce COVID-19 morbidity and mortality,” said Dr. Telenti. “We were thrilled to successfully contribute to this challenge with our model and hope that these efforts will foster a new generation of decision support tools that will result in improved patient care and outcomes.”
“This award and acknowledgement from BARDA and HHS speak not only to the capabilities of our world-class scientists, but also to our leadership in developing and leveraging impactful artificial intelligence and machine learning technologies. We deploy these cutting-edge tools each day, as we work across our pipeline to better understand and treat infectious diseases,” said George Scangos, Ph.D., chief executive officer of Vir Biotechnology. “We are proud to contribute a new technology that can accurately forecast burden of disease for patients and hospital systems – a critical component of pandemic preparedness and real-time response.”
The Pediatric COVID-19 Data Challenge award included a $200,000 cash prize from BARDA, of which was split between the winning Vir team and the Department of Biostatistics & Medical Informatics (BMI) at the University of Wisconsin-Madison.
About Vir Biotechnology
Vir Biotechnology is a commercial-stage immunology company focused on combining immunologic insights with cutting-edge technologies to treat and prevent serious infectious diseases. Vir has assembled four technology platforms that are designed to stimulate and enhance the immune system by exploiting critical observations of natural immune processes. Its current development pipeline consists of product candidates targeting COVID-19, hepatitis B virus, influenza A and human immunodeficiency virus. We routinely post information that may be important to investors on our website at www.vir.bio.
Vir Forward-Looking Statements
This press release contains forward-looking statements within the meaning of the Private Securities Litigation Reform Act of 1995. Words such as “may,” “will,” “plan,” “potential,” “aim,” “promising” and similar expressions (as well as other words or expressions referencing future events, conditions or circumstances) are intended to identify forward-looking statements. These forward-looking statements are based on Vir’s expectations and assumptions as of the date of this press release. Forward-looking statements contained in this press release include, but are not limited to, statements regarding the ability of our machine learning model to result in improved patient care and outcomes and accurately forecast burden of disease for patients and hospital systems. Many factors may cause differences between current expectations and actual results. Factors that may cause actual results to differ from those expressed or implied in the forward-looking statements in this press release are discussed in Vir’s filings with the U.S. Securities and Exchange Commission, including the section titled “Risk Factors” contained therein.
