We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us

Download Mobile App





AI Tool Predicts Which COVID-19 Patients Can Develop Severe Respiratory Disease

By HospiMedica International staff writers
Posted on 01 Apr 2020
Print article
Illustration
Illustration
A new study has found that an artificial intelligence (AI) tool can accurately predict which patients who have been newly infected with the 2019 coronavirus disease (COVID-19) can go on to develop severe respiratory disease. The study was led by the NYU Grossman School of Medicine (New York City, NY) and NYU Courant Institute of Mathematical Sciences (New York City, NY) in partnership with Wenzhou Central Hospital (Wenzhou, China) and Cangnan People’s Hospital (Wenzhou, China). The study also revealed the best indicators of future severity, and found that they were not as expected.

For the study, the researchers gathered demographic, laboratory, and radiological findings collected from 53 patients who tested positive in January 2020 for the SARS-CoV-2 virus at the two Chinese hospitals. The patients initially had typically mild symptoms, including cough, fever, and stomach upset, although severe symptoms, including pneumonia, developed in a minority of patients within a week. The study aimed to determine whether AI techniques could help to accurately predict which patients with the virus would go on to develop acute respiratory distress syndrome (ARDS). The researchers also designed computer models that make decisions based on the data fed into them, with the programs becoming “smarter” with more data that they considered. The study used decision trees that track series of decisions between options and that model the potential consequences of choices at each step in a pathway.

The researchers were surprised to find that certain patterns seen in lung images, fever, and strong immune responses, were not useful in predicting which patients with initial, mild symptoms would go on to develop severe lung disease. Instead, the researchers found that the new AI tool identified changes in three features—levels of the liver enzyme alanine aminotransferase (ALT), reported myalgia, and hemoglobin levels—which were most accurately predictive of subsequent, severe disease. This, combined with other factors, allowed the AI tool to predict the risk of ARDS in patients infected with COVID-19 with up to 80% accuracy.

“While work remains to further validate our model, it holds promise as another tool to predict the patients most vulnerable to the virus, but only in support of physicians’ hard-won clinical experience in treating viral infections,” said corresponding study author Megan Coffee, MD, PhD, clinical assistant professor in the Department of Medicine and member of the Division of Infectious Diseases and Immunology at NYU Langone.

“Our goal was to design and deploy a decision-support tool using AI capabilities—mostly predictive analytics—to flag future clinical coronavirus severity,” said co-author Anasse Bari, PhD, a clinical assistant professor in computer science at NYU Courant Institute of Mathematical Science. “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, when hospital resources are stretched thin.”

Related Links:
NYU Grossman School of Medicine
NYU Courant Institute of Mathematical Sciences


Gold Member
POC Blood Gas Analyzer
Stat Profile Prime Plus
Gold Member
Real-Time Diagnostics Onscreen Viewer
GEMweb Live
Silver Member
Wireless Mobile ECG Recorder
NR-1207-3/NR-1207-E
New
Stereotactic Ultralight System
SUSy

Print article

Channels

Critical Care

view channel
Image: The permeable wearable electronics developed for long-term biosignal monitoring (Photo courtesy of CityUHK)

Super Permeable Wearable Electronics Enable Long-Term Biosignal Monitoring

Wearable electronics have become integral to enhancing health and fitness by offering continuous tracking of physiological signals over extended periods. This monitoring is crucial for understanding an... Read more

Surgical Techniques

view channel
Image: NTT and Olympus have begun the world\'s first joint demonstration experiment of a cloud endoscopy system (Photo courtesy of Olympus)

Cloud Endoscopy System Enables Real-Time Image Processing on the Cloud

Endoscopes, which are flexible tubes inserted into the body's natural openings for internal examination and biopsy collection, are becoming increasingly vital in medical diagnostics. Their minimal invasiveness... Read more

Patient Care

view channel
Image: The newly-launched solution can transform operating room scheduling and boost utilization rates (Photo courtesy of Fujitsu)

Surgical Capacity Optimization Solution Helps Hospitals Boost OR Utilization

An innovative solution has the capability to transform surgical capacity utilization by targeting the root cause of surgical block time inefficiencies. Fujitsu Limited’s (Tokyo, Japan) Surgical Capacity... Read more

Health IT

view channel
Image: First ever institution-specific model provides significant performance advantage over current population-derived models (Photo courtesy of Mount Sinai)

Machine Learning Model Improves Mortality Risk Prediction for Cardiac Surgery Patients

Machine learning algorithms have been deployed to create predictive models in various medical fields, with some demonstrating improved outcomes compared to their standard-of-care counterparts.... Read more

Point of Care

view channel
Image: The PATHFAST hs-cTnI-II high-sensitivity troponin assay has been developed for the PATHFAST Biomarker Analyzer (Photo courtesy of Polymedco)

POC Myocardial Infarction Test Delivers Results in 17 Minutes

Chest pain is the second leading cause of emergency department (ED) visits by adults in the United States, generating over 7 million visits annually. In the event of a suspected heart attack, physicians... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.