Virus World

Versiti’s blood tests screen for antibodies that may make typical clot treatments harmful to help healthcare providers choose alternative therapies.  Following international probes into rare blood clots among recipients of Johnson & Johnson and AstraZeneca’s COVID-19 vaccines, blood testing company Versiti has put forward a suite of antibody tests to help identify patients that may be at risk. While these cases only number in the dozens among the millions of shots administered worldwide, one of the more dangerous aspects of these potentially severe clots—known as cerebral venous sinus thrombosis—is that the typical anticoagulation treatment can make matters worse. The blood thinner heparin is often used to treat blood clots, but in patients carrying certain platelet-activating antibodies, heparin can trigger harmful drops in platelet counts that could lead to spontaneous bleeding, worsening of their original clots and other complications, according to the Centers for Disease Control and Prevention (CDC).  

Versiti’s blood tests screen for these antibodies, to help healthcare providers choose alternative anticoagulation therapies.  They include an ELISA diagnostic for the PF4, heparin-dependent antibody, followed by additional heparin-induced thrombocytopenia testing or serotonin release assays, depending on the initial result.  The company also offers antibody identification panels if the patient shows low platelet counts in a standard blood draw. The American Society of Hematology recommends testing for PF4 antibodies ahead of treatment for vaccine-induced thrombotic thrombocytopenia, which it describes as an evolving disorder based on limited data.  After a 10-day pause on the use of the J&J vaccine in the U.S.—while the FDA and other agencies reviewed safety data, including the deaths of three recipients—a CDC advisory panel last week recommended restarting nationwide distribution. The shot, like AstraZeneca’s, will carry warnings about rare and severe blood clots and guidance for proper treatment. Both use adenovirus-based vectors to deliver the vaccine’s instructions into human cells.

Versiti's Press Release (April 27, 2021):

https://www.versiti.org/newsroom/news-releases/versiti-unveils-new-testing-options-for-vaccine-in 

Accurate diagnostic strategies to rapidly identify SARS-CoV-2 positive individuals for management of patient care and protection of health care personnel are urgently needed. The predominant diagnostic test is viral RNA detection by RT-PCR from nasopharyngeal swabs specimens, however the results of this test are not promptly obtainable in all patient care locations. Routine laboratory testing, in contrast, is readily available with a turn-around time (TAT) usually within 1-2 hours. 

Here we present a machine learning model incorporating patient demographic features (age, sex, race) with 27 routine laboratory tests to predict an individual's SARS-CoV-2 infection status. Laboratory test results obtained within two days before the release of SARS-CoV-2-RT-PCR result were used to train a gradient boosted decision tree (GBDT) model from 3,346 SARS-CoV-2 RT-PCR tested patients (1,394 positive and 1,952 negative) evaluated at a large metropolitan hospital. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.853 (95% CI: 0.829-0.878). Application of this model to an independent patient dataset from a separate hospital resulted in a comparable AUC (0.838), validating the generalization of its use. Moreover, our model predicted initial SARS-CoV-2 RT-PCR positivity in 66% individuals whose RT-PCR result changed from negative to positive within two days. 

Overall, this model employing routine laboratory test results offers opportunities for early and rapid identification of high-risk SARS-COV-2 infected patients before their RT-PCR results are available. This may facilitate patient care and quarantine, indicate who requires retesting, and direct personal protective equipment use while awaiting definitive RT-PCR results.

Preprint available at medRxiv (June 19, 2020):

https://doi.org/10.1101/2020.06.17.20133892