Six key numbers that can predict your risk of life-threatening Covid
Just six numbers — fed into a new analytical tool — can predict which patients with COVID-19 will go on to develop life-threatening infections.
This is the report of a team of researchers from Rutgers University who used machine learning to create a simple-to-use prognostic model for Covid outcomes.
Their formula, which they hope to introduce into tools commonly used by doctors, requires just the patient’s age and five other measurements hospitals are already routinely collecting.
After developing their model based on analyses of data on more than 950 patients who had been hospitalized with Covid, they showed that it could successfully predict disease progressions in two other patient groups.
These included 7,901 patients hospitalized in the pre-vaccination period of the pandemic, as well as 1,547 individuals from the period after vaccines became available — i.e. when the original virus had been superseded by later variants.
READ MORE:
Dr Fauci was ‘sneaked’ into CIA to ‘influence’ investigation into Covid origins
New COVID-19 hotspot map shows exactly where latest variant is spreading
The study was undertaken by Professor of medicine Payal Parikh of Rutgers University—New Brunswick and her colleagues.
Parikh said: “Accurate prognoses are extremely valuable. They let patients understand what’s coming while they’re still healthy enough to make informed treatment choices.
“They also let hospitals allocate resources efficiently by anticipating patient needs.
“With better prognostication, we can start treatment early in the disease process, which leads to better patient care outcomes.”
To develop their prediction system, the team started with the medical records of 969 people who had been hospitalized with SARS-CoV-2 — the virus that causes COVID-19.
Lead paper author David Natanov explained: “We took a bunch of data points from each patient — lab results, demographics, vital signs, comorbidities, and dozens more.
“We pumped that through a series of different machine learning models tuned to slightly different parameters and generated an initial 77-variable model.”
He quipped: “That model performed well but no-one has time to enter 77 separate data points into anything!”
We use your sign-up to provide content in ways you’ve consented to and to improve our understanding of you. This may include adverts from us and 3rd parties based on our understanding. You can unsubscribe at any time. More info
DON’T MISS:
Doctor shares three red flag signs of brain tumours – ‘See a GP'[CANCER]
Dr Michael Mosley shares the unripe fruit that could lower bowel cancer risk[HEALTH RISK]
To make the model more practical, the researchers next used analytic tools to identify the 10 variables of the original 77 that were the most predictive of Covid outcomes.
They then used artificial intelligence to explore the strength of various combinations of these — identifying two effective models in particular that need only six of the data points.
These six variables are platelet count, lactace, age, blood urea nitrogen, aspartate aminotransferase and C-reactive protein, all of which hospitals regularly track.
The researchers have named the most accurate of the two models after the first letter of each of these parameters — that is, “PLABAC”.
According to the team, a key advantage of their prognostic model is how simple it is to use — at present, all clinicians need to do is enter the six variables into a formula — and the team think that they can make it easier still.
Natanov explained: “I plan to reach out to MDCalc, an app that every clinician has on their phone to look stuff up and use helpful formulas.
“I’d love to get the formula for this added so users could get a prognosis simply by typing in the six numbers.”
The researchers said that he would also like to work with Epic — the largest producer of electronic health record software — to add the PLABAC model to the firm’s growing list of predictive tools.
If such went ahead, he explained: “No one would have to enter anything. The system would just automatically pull the numbers from the lab results and make the calculations.”
Daily Express US has reached out to Epic and MDCalc for comment.
The full findings of the study were published in the journal mBio.
Follow our social media accounts on https://www.facebook.com/ExpressUSNews and @ExpressUSNews
Source: Read Full Article