APR 04, 2020 2:00 PM PDT

AI Finds New Predictive Markers of Covid-19 Severity

WRITTEN BY: Tara Fernandez

 

Researchers and healthcare organizations are putting their heads together to consider how technology could ease the ever-worsening COVID-19 global crisis. A partnership between NYU and the hospitals in Wenzhou, China are turning to artificial intelligence (AI) to help predict exactly which COVID-19 patients go on to develop severe respiratory disease.

Symptoms for COVID-19, including cough, fever, and difficulty breathing start to appear after an incubation phase that can take as long as two weeks. According to research, around 80 percent of infected individuals experience the mild form of the coronavirus infection. Individuals at risk for developing severe complications from infection are those with underlying health complications, such as heart disease, diabetes, and cancer. However, correlating the severity of the disease with health status at the time of infection may not be as straightforward as initially thought.

Data collected from over 50 COVID-19 patients admitted to Wenzhou Central Hospital and Cangnan People's Hospital revealed an unexpected trend. A small subset of patients who were healthy at the time of infection and experienced mild symptoms subsequently progressed to a very severe, life-threatening form of the disease. Caught off guard, physicians struggled to improve patient outcomes in these cases. 

The study, published in Computers, Materials & Continua, aimed to determine whether AI-powered tools could assist in pinpointing exactly which patients are most likely to develop Acute Respiratory Distress Syndrome (ARDS) — a common cause of death in critically ill COVID-19 patients.

The research teams fed their AI-driven computer model with COVID-19 data, in the form of demographic, laboratory, and radiological findings, with the program “learning” to pick out hidden patterns connecting this data to clinical outcomes. Interestingly, features once thought to be strong predictors of downstream disease severity (opacity in lung X-rays, the intensity of the immune response, age, and gender) turned out to not be as significant.

Instead, the program made associations between disease severity and three specific markers: levels of a patient’s alanine aminotransferase (a liver enzyme), blood hemoglobin, and deep muscle pain. According to the research team, these and other factors enabled them to use their AI tool to predict the future onset of ARDS with 80 percent accuracy.

Co-author Anasse Bari, a computer science  expert at the Courant Institute said, “We hope that the tool, when fully developed, will be useful to physicians as they assess which moderately ill patients really need beds and who can safely go home, with hospital resources stretched thin.”

 

 


Sources: NYU, Computers, Materials & Continua.

About the Author
  • Tara Fernandez has a PhD in Cell Biology and has spent over a decade uncovering the molecular basis of diseases ranging from skin cancer to obesity and diabetes. She currently works on developing and marketing disruptive new technologies in the biotechnology industry. Her areas of interest include innovation in molecular diagnostics, cell therapies, and immunology. She actively participates in various science communication and public engagement initiatives to promote STEM in the community.
You May Also Like
APR 12, 2021
Microbiology
New Lyme Test Can ID The DIsease Early
APR 12, 2021
New Lyme Test Can ID The DIsease Early
Lyme disease is a disease that is caused by four main species of bacteria, including Borrelia burgdorferi, which ar ...
MAY 18, 2021
Clinical & Molecular DX
A Crystal Ball for Predicting Labor Day
MAY 18, 2021
A Crystal Ball for Predicting Labor Day
Expectant mothers may no longer have to be caught off guard—researchers have identified biomarkers in the blood th ...
MAY 24, 2021
Clinical & Molecular DX
Discovery of Viral Peptides Paves the Way for Cheaper, More Accurate COVID Diagnostics
MAY 24, 2021
Discovery of Viral Peptides Paves the Way for Cheaper, More Accurate COVID Diagnostics
Over 1.5 billion vaccine doses have been administered worldwide, but SARS-CoV-2 variants are now threatening efforts to ...
JUL 15, 2021
Clinical & Molecular DX
Childhood Lead Exposure Influences Personality in Adulthood
JUL 15, 2021
Childhood Lead Exposure Influences Personality in Adulthood
Exposure to toxic chemicals in childhood could have unlikely effects on personality, and behavioral traits in adulthood, ...
AUG 17, 2021
Clinical & Molecular DX
Sleep Apnea Doubles the Risk of Sudden Death
AUG 17, 2021
Sleep Apnea Doubles the Risk of Sudden Death
Obstructive sleep apnea, or OSA, is the most commonly reported sleep disorder, with loud snoring being one of the tell-t ...
SEP 06, 2021
Cancer
A New Biomarker to Personalize Breast Cancer Therapy
SEP 06, 2021
A New Biomarker to Personalize Breast Cancer Therapy
The American Cancer Society estimates that over 280,000 women in the United States will be diagnosed with breast cancer ...
Loading Comments...