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 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

Gold Supplier
Creatinine Meter
StatSensor Xpress Creatinine Meter
New
Surgical Instruments
Laparoscopic Bariatric Surgery Instrument Set
New
Specimen Radiography System
TrueView Pro 100
New
Hyper-Hypothermia Blanket
Maxi-Therm

Print article
Radcal

Channels

Critical Care

view channel
Image: An earbud prototype that has been wired for data collection (Photo courtesy of MUSC)

Earbuds to Outperform Smartwatches in Monitoring Blood Pressure

While blood pressure cuffs are considered the most accurate method of measurement, they require the user to sit down, put on the cuff, and stay still. This can be inconvenient and may lead to errors in... Read more

Surgical Techniques

view channel
Image: New robust thermosensitive bioadhesives can improve surgical sealing (Photo courtesy of Pexels)

New Surgical Sealing Biomaterial Could Eliminate Standard Methods of Suturing and Stapling

For surgical wounds to be properly closed, the sealant material used must effectively seal on wet, slippery tissue surfaces that vary in shape and may involve tissue movement, such as an expanding lung,... Read more

Health IT

view channel
Image: Using digital data can improve health outcomes (Photo courtesy of Unsplash)

Electronic Health Records May Be Key to Improving Patient Care, Study Finds

When a patient gets transferred from a hospital to a nearby specialist or rehabilitation facility, it is often difficult for personnel at the new facility to access the patient’s electronic health records... Read more

Business

view channel
Image: The demand for endometrial ablation devices is increasing due to rising prevalence of gynecological disorders (Photo courtesy of Pexels)

Global Endometrial Ablation Market Driven by Rising Prevalence of Gynecological Disorders

Gynecological disorders, such as menorrhagia, PCOD, abnormal vaginal bleeding, affect millions of women globally every year and are on the rise. Abnormal Uterine Bleeding (AUB) is the most common disorder... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.