New York, NY (WorkersCompensation.com) – The College of Dentistry at New York University (NYU) announced the development of a portable app that can help providers determine which of their COVID-19 patients are the most likely to become a severe case. The app uses artificial intelligence to cross reference a patient’s risk factors with their lab work to determine a COVID-19 “severity score.”
While there is a test for COVID-19 to determine whether a patient is infected, there is currently no way for providers to determine just how sick a patient may become from the virus. Lead NYU researcher John T. McDevitt, PhD believes having such a tool to assist providers would be beneficial in reservation of resources stating, “Identifying and monitoring those at risk for severe cases could help hospitals prioritize care and allocate resources like ICU beds and ventilators. Likewise, knowing who is at low risk for complications could help reduce hospital admissions while these patients are safely managed at home.”
To develop the tool, researchers analyzed data from 160 hospitalized patients in Wuhan, China. The researchers discovered that there were 4 key factors in blood tests that were significantly elevated in patients that died in comparison to those that recovered. The four elevated lab markers included
- C-reactive protein (CRP)
- Myoglobin (MYO)
- Procalcitonin (PCT)
- Cardiac troponin I (ctni)
Elevated levels are often seen with acute inflammation, lower respiratory tract infections, and compromised cardiovascular health.
Researchers created a model inputting the lab and risk data. Utilizing artificial intelligence and algorithms, the team defined patterns of COVID-19 to calculate the potential severity of the disease. This resulted in a severity score of 0 for mild to moderate, and up to 100 for severe.
To validate their findings, the team tested 12 hospitalized cases from Shenzhen, China. The app scored deceased patients at a severity rate significantly higher than those that were discharged. The findings were published in Lab on a Chip, a journal of the Royal Society of Chemistry. The app was then evaluated at the Family Health Centers at NYU Langone after validation.
The app uses minimal amounts of saliva or blood applied to small cartridges with implanted bio-nano-chips that were engineered by McDevitt. A portable analyzer then reads the specimens on the chips and provides results in approximately a half hour. The app can be used with pre-existing lab tests.
McDevitt in partnership with SensoDx has plans to develop a product that can produce test results on the spot similar to insulin test kits.