Clinical Decision Support Tool and Rapid Point-of-Care Platform for Determining Disease Severity in Patients with COVID-19

Abstract

SARS-CoV-2 is the virus that causes coronavirus disease (COVID-19) which has reached pandemic levels resulting in significant morbidity and mortality affecting every inhabited continent. The large number of patients requiring intensive care threatens to overwhelm healthcare systems globally. Likewise, there is a compelling need for a COVID-19 disease severity test to prioritize care and resources for patients at elevated risk of mortality. Here, an integrated point-of-care COVID-19 Severity Score and clinical decision support system is presented using biomarker measurements of C-reactive protein (CRP), N-terminus pro B type natriuretic peptide (NT-proBNP), myoglobin (MYO), D-dimer, procalcitonin (PCT), creatine kinase-myocardial band (CK-MB), and cardiac troponin I (cTnI). The COVID-19 Severity Score combines multiplex biomarker measurements and risk factors in a statistical learning algorithm to predict mortality. The COVID-19 Severity Score was trained and evaluated using data from 160 hospitalized COVID-19 patients from Wuhan, China. Our analysis finds that COVID-19 Severity Scores were significantly higher for the group that died versus the group that was discharged with median (interquartile range) scores of 59 (40-83) and 9 (6-17), respectively, and area under the curve of 0.94 (95% CI 0.89-0.99). These promising initial models pave the way for a point-of-care COVID-19 Severity Score system to impact patient care after further validation with externally collected clinical data. Clinical decision support tools for COVID-19 have strong potential to empower healthcare providers to save lives by prioritizing critical care in patients at high risk for adverse outcomes.

Figure 1.

The p-BNC assay system consists of a disposable cartridge (A) and a portable instrument (B). The instrument facilitates fluid motivation inside the cartridge by crushing the fluid filled blister packs on the cartridge surface and reads the resulting optical fluorescent signal generated on bead sensors (C) (from left to right: SEM image of the cartridge’s bead array chip; fluorescent photomicrograph of the bead sensors; an agarose bead sensor with immunofluorescent signal; illustration of a sandwich immunoassay on agarose bead fibers).

Figure 2.

Programmable cartridge for COVID-19 diagnostics. The p-BNC cartridge features 20 spatially programmable bead sensors (A) that can be customized for a multitude of applications. Here, two panels are detailed for COVID-19: a disease severity panel as featured in the work (B) and a community exposure / surveillance panel as will be described in future efforts (C).

Figure 3.

Standard curves generated for a COVID-19 disease severity biomarker panel including cTnI, CK-MB, myoglobin, and NT-proBNP.

Figure 4.

COVID-19 Severity Scores from internal model validation. A model was trained on data from hospitalized COVID-19 patients of which 117 were discharged and 43 died. The COVID-19 Severity Score is a numerical index between 0 and 100 that indicates the probability of COVID-19 mortality. Individual patient scores are represented as scatter dots with overlaid boxplots showing the population distribution.

Figure 5.

Initial rough scale for COVID-19 Severity Score based on the CDC’s Interim Clinical Guidance for Management of Patients with Confirmed COVID-19. The continuous scale COVID-19 Severity Score has the potential to assist the identification of patients with severe/critical disease status.

Figure 6.

COVID-19 Severity Scores evaluated for a case study of 12 hospitalized patients with COVID-19 from Shenzhen, China. The Moderate group contained patients whose only complication was pneumonia. The Severe group were patients with pneumonia and ARDS. The Critical group contained patients with one or more of severe ARDS, respiratory failure, cardiac failure, or shock.