CHIP Faculty Members Collaborate on Study Using Artificial Intelligence to Help Confirm Negative COVID-19 Patients

CHIP Faculty Members Al’ona Furmanchuk, PhD, Faraz Ahmad, MD, MS, David Liebovitz, MD, and CHIP Director Abel Kho, MD, MS, co-authored the study, “A predictive tool for identification of SARS-CoV-2 PCR-negative emergency department patients using routine test results,” published in the August 2020 issue of the Journal of Clinical Virology.

Around the world, health care systems have struggled to meet the demands of the COVID-19 pandemic. As healthcare workers exercise utmost caution with patients who may be COVID-19 positive, they are often required to misuse health system resources while waiting for SARS-CoV-2, the virus that causes COVID-19, test results.

This study aimed to develop a tool that could use readily available, routine lab values to help clinicians predict negative COVID-19 patients and, thus, protect healthcare workers and preserve their limited supplies of SARS-CoV-2 tests, personal protective equipment (PPE), and other resources.

The study team developed a predictive model to help differentiate between COVID-19 positive and negative patients when SARS-CoV-2 tests are not available or inconclusive. The study specifically focused on patients presenting to the emergency department (ED), where accurate and efficient decision making is vital to patient survival and healthcare worker safety.

The study found that this model could be used to provide clinicians with a complementary tool to make decisions about triaging patients. Additionally, the study found some potential for routine utilization of this tool to ensure the safety of healthcare workers when working with asymptomatic COVID-19 patients being treated in the emergency department for non-COVID-19 related illness and injury.

The collaborative study team included researchers from across the world. Researchers at Stanford University developed a predictive model, and teams at Northwestern University, the University of Washington, and the University of Ulsan College of Medicine and Asan Medical Center, Bundang Jesaeng General Hospital, and U2Bio Laboratories in South Korea, validated the model.

The study team included Rohan P. Joshi, Vikas Pejaver, Noah E. Hammarlund, Heungsup Sung, Seong Kyu Leed, Hye-Young Lee, Gregory Scott, Saurabh Gombar, Nigam Shah, Sam Shen, Anna Nassiri, Daniel Schneider, Sean Mooney, Benjamin A. Pinsky, and Niaz Banaei.

View the publication: https://doi.org/10.1016/j.jcv.2020.104502

« Back To News

Join Us

CHIP collaborators are part of the public, private and nonprofit sectors and have an interest in working toward a world where health outcomes are improved because data is used effectively.

Get in Touch

Join Our Mailing List

Don't Forget To Connect