Seasons Greetings

Flash News: D.C. Mayor Has 'Black Lives Matter' Painted Near White House     - | -     Trump Tried to Register to Vote in Florida with Address of White House     - | -     Google Says Both China and Iran Are Trying to Hack Presidential Campaigns     - | -     John Kelly Backs Mattis to Join the Chorus Going Against Trump     - | -     Trump Sued by Black Lives Matter for Using Force on Peaceful Protesters     - | -     Obama Asks Mayors to Act to Stomp Out 'Systemic Racism'     - | -     This Is What GOP Feared. Now that Trump Has Governed with Executive Orders, Dems Plan to Do Same      - | -     Man Throwing 'Incendiary Devices' at ICE Detention Center Is Killed in Attack      - | -     Mueller Hearing Pushed Back a Week to Allow More Time for Him to Answer Questions      - | -     Trump Tells 4 Congresswomen of Color to 'Go Back' to 'Crime-Infested' Countries They Came From      - | -     GOP Congressman Invokes 'The Deep State'

Breaking News: D.C. Mayor Has 'Black Lives Matter' Painted Near White House... Readmore

Features & Columns

Coronavirus Model Can Predict Risk of Death 10 Days Before

viewsViews 140

Coronavirus Model Can Predict Risk of Death 10 Days Before

2020-05-21 19:07:59

By Laura Tucker, Staff writer; Image: Doctor carrying PPE (Image source: Public domain)


Four months after first hearing about the novel coronavirus, it seems like the experts know both a great deal and very little about the virus. It's still surprising the experts with regard to new symptoms, reactions, how it can be passed, etc. That makes it quite unsettling to the general public who are left unsure of when they're really safe or unsafe.


Because of this, there has been so much conflicting information about coronavirus COVID-19: No need to wear a mask unless you want to; never wear a mask; wear a mask if you want to; never leave your home without a mask; you're safe unless you are elderly or high risk; people outside of major clusters are safe; no one is safe, do not leave your home; still no one is safe, but you can leave your house anyway. 

One shining light has popped up in a new study that may help the public feel a little safer. While symptoms have varied so much and patients can seem to be dealing with the virus and then will suddenly be struck down and die very quickly, this study believes the model it created can pinpoint the dangers up to 10 days before.


The Nature Machine Intelligence journal published a study last week that explained researchers created a model with three biological markers that are found in COVID-19 patients' blood. This could indicate whether the patient could become seriously ill and possibly die more than 10 days ahead of time. It's said to have 90 percent accuracy. 

These researchers believe these markers will be a way to separate "the vast majority of cases that require immediate medical attention." The authors contend the model can provide a "simple and intuitive clinical test to precisely and quickly quantify the risk of death."


Since the beginning the experts have been saying that people with underlying conditions or who are older are at a greater risk of COVID-19 becoming fatal if they contract it.  

Additionally, health-care personnel have been saying they are being forced to prioritize cases because the health system is so overwhelmed. They are forced to give preferential treatment to those who they believe have the best chance of making it, while leaving those with the least chance without every heroic option. This means elderly patients and those with underlying conditions are sometimes left out of treatment.


Using these biological markers, however, can give health-care workers advance notice of which patients will require more drastic treatment. Instead of separating them via their chances of surviving based on their age or underlying medical conditions, they can give the people who are at most risk treatment while just keeping a watchful eye on those who aren't as much as risk. 

To identify the common biological markers that indicate a higher risk, researchers analyzed the blood samples of 485 patients at Tongi Hospital in Wuhan, China, between January 10 and February 18.


The blood samples were tested for kidney, heart, and other blood clotting issues, while it was noted which patients survived and which ones died. A machine-learning algorithm was then applied to search for patterns in those biological markers. 

One of those markers is high levels of the lactic dehydrogenase (LDH) that is associated with lung damage and tissue breakdown. These are issues seen in pneumonia cases.


Another marker is low levels of lymphocytes — the white blood cells that fight pathogens such as COVID-19. The final marker is an increase in high-sensitivity C-reactive proteins. These indicate there is inflammation in the lungs. 

If a patient has all three of those markers, the computer model can predict how likely it is the patient will die from COVID-19 up to 10 days in advance.


"The three key features, LDH, lymphocytes, and hs-CRP, can be easily collected in any hospital," wrote the researchers in the study. "In crowded hospitals, and with shortages of medical resources, this simple model can help to quickly prioritize patients, especially during a pandemic when limited healthcare resources have to be allocated." 

Another study was published in the Journal of the American Medical Association on Tuesday. It appears to back the other study's findings. The study in the AMA Journal examined 10 biomarkers that could help assess the risk of a patient becoming critical or dying from the virus.


Two of those biomarkers are the same as the first study: high levels of LDH and a high neutrophil to lymphocyte ratio (associated with lower levels of lymphocytes). 

The other risk factors in the AMA Journal include a history of cancer, high number of preexisting conditions, elderly, shortness of breath, coughing up blood, unconsciousness, abnormal chest x-rays, and high levels of bilirubin, an indicator of liver damage.


Using this set of 10 biomarkers, researchers created a "coronavirus risk calculator" that can be accessed on the Web. Like the other study's three biomarkers, this risk calculator can help predict which patients will become critically ill. 

"If the patient's estimated risk of critical illness is low, the clinician may choose to monitor, whereas high-risk estimates might support aggressive treatment or admission to the ICU," said the study.

Post Your Comment

Most Recent News

D.C. Mayor Has 'Black Lives Matter' Painted Near White House

6 June, 2020

WASHINGTON (Reuters) - The mayor of Washington, D.C., had the slogan “Black Lives Matter” painted in massive yellow letters on a street leading to the White House on Friday in tribute......More

Trump's Reaction Boosted Support For Kaepernick and Black Lives Matter According to Professor

6 June, 2020

  Trump's Reaction Boosted Support For Kaepernick and Black Lives Matter  ...More

Golf: Paul McGinley Sets New World Record on the Putting Green

6 June, 2020

  Paul McGinley sets new world record on the putting green  ...More