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
RANDOX LABORATORIES

Download Mobile App





AI Predicts COVID Prognosis at Near-Expert Level Based Off CT Scans

By HospiMedica International staff writers
Posted on 05 Apr 2022
Print article
Image: Chest CT deep learning algorithm quantifies COVID-19 lung disease (Photo courtesy of Pexels)
Image: Chest CT deep learning algorithm quantifies COVID-19 lung disease (Photo courtesy of Pexels)

A new study to evaluate the ability of a chest CT deep learning algorithm for quantification of COVID-19 lung disease found that it was highly predictive of inpatient outcomes and performed at a near expert level.

Investigators at the Medical University of South Carolina (Charleston, SC, USA) evaluated the ability of a deep convolutional neural network (dCNN) to predict inpatient outcomes associated with COVID-19 pneumonia. For the study, a previously trained dCNN was tested on an external validation cohort of 241 patients who presented to the emergency department and received a chest CT scan, 93 with COVID-19 and 168 without. Airspace opacity scoring systems were defined by the extent of airspace opacity in each lobe, totaled across the entire lungs. Expert and dCNN scores were concurrently evaluated for interobserver agreement, while both dCNN identified airspace opacity scoring and raw opacity values were used in the prediction of COVID-19 diagnosis and inpatient outcomes.

The study revealed that interobserver agreement for airspace opacity scoring was 0.892 (95% CI 0.834-0.930). The probability of each outcome behaved as a logistic function of the opacity scoring (25% ICU admission at score of 13/25, 25% intubation at 17/25, and 25% mortality at 20/25). The study also found that the length of hospitalization, ICU stay, and intubation were associated with larger airspace opacity score (p = 0.032, 0.039, 0.036, respectively). Based on these findings, the researchers concluded that the tested dCNN was highly predictive of inpatient outcomes, can perform at a near expert level, and provide added value for clinicians in terms of prognostication and disease severity.

“The use of artificial intelligence deep learning models to prognosticate from CT images has been identified from the beginning of the pandemic as a potential way to expedite the triage process, improve prognostication, and guideline utilization of resources,” explained corresponding author U. Joseph Schoepf, MD, from the Division of Cardiovascular Imaging at the Medical University of South Carolina in Charleston. “Utilizing AI severity scoring may be helpful in meeting the challenge of practical, reproducible triage of COVID-19 patients by identifying patients at high risk for morbidity and mortality.”

Related Links:
Medical University of South Carolina

Platinum Supplier
STI Test
Vivalytic Sexually Transmitted Infection (STI) Array
Gold Supplier
Enteral Feeding Pump
SENTINELplus
New
Volumetric Infusion Pump
CODAN A717V Plus/A718V Plus
New
Gold Supplier
IMRT Thorax Phantom
CIRS Model 002LFC

Print article
Radcal

Channels

Critical Care

view channel
Image: Flexible thin-film electrodes placed directly on brain tissue have shown promise for diagnosis and treatment of epilepsy (Photo courtesy of Tokyo Tech)

Thin-Film Neural Electrodes Placed Directly on Brain Tissue Can Diagnose and Treat Epilepsy

Analyzing brain activity is crucial for diagnosing conditions like epilepsy and other mental health disorders. Among various methods, electroencephalography (EEG) is considered the least intrusive, using... Read more

Surgical Techniques

view channel
Image: The Canady Robotic AI Surgical System (Photo courtesy of JCRI-ABTS)

AI Robotic System Selectively Kills Microscopic Tumor Cells without Damaging Surrounding Tissue

When treating cancer, surgeons usually aim to remove the tumor along with a surrounding "margin" of healthy tissue to make sure all cancer cells have been taken out. However, even with advancements in... 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 broad-spectrum POC coagulometer is well-suited for emergency room and emergency vehicle use (Photo courtesy of Perosphere)

Novel POC Coagulometer with Lab-Like Precision to Revolutionize Coagulation Testing

In emergency settings, when patients arrive with a bleed or require urgent surgery, doctors rely solely on clinical judgment to determine if a patient is adequately anticoagulated for reversal treatment.... Read more

Business

view channel
Image: The global surgical lights market is expected to grow by close to USD 0.50 billion from 2022 to 2027 (Photo courtesy of Freepik)

Global Surgical Lights Market Driven by Increasing Number of Procedures

The global surgical lights market is set to witness high growth, largely due to the increasing incidence of chronic illnesses, a surge in demand for cosmetic and plastic surgeries, and untapped opportunities... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.