PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Deep-learning chest radiograph model predicts mortality for community-acquired pneumonia

A deep learning-based model using initial chest radiographs predicted 30-day mortality in patients with community-acquired pneumonia, improving upon the performance of an established risk prediction tool

Deep-learning chest radiograph model predicts mortality for community-acquired pneumonia
2023-06-30
(Press-News.org) Leesburg, VA, June 30, 2023—According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR), a deep learning-based model using initial chest radiographs predicted 30-day mortality in patients with community-acquired pneumonia (CAP), improving upon the performance of an established risk prediction tool (i.e., CURB-65 score).

“The deep learning (DL) model may guide clinical decision-making in the management of patients with CAP by identifying high-risk patients who warrant hospitalization and intensive treatment,” concluded first author Eui Jin Hwang, MD, PhD, from the department of radiology at Seoul National University College of Medicine in Korea.

In this AJR accepted manuscript, a DL model was developed in 7,105 patients via one institution from March 2013 to December 2019 (3:1:1 allocation to training, validation, and internal test sets) to predict risk of all-cause mortality within 30 days after CAP diagnosis using patients’ initial chest radiograph. Hwang et al. then evaluated their DL model in patients diagnosed with CAP during emergency department visits at the same institution as the development cohort from January 2020 to December 2020 [temporal test cohort (n = 947)], and from two additional different institutions [external test cohort A (n = 467), January 2020 to December 2020; external test cohort B (n = 381), March 2019 to October 2021]. AUCs were compared between the DL model and a risk score based on confusion, blood urea nitrogen level, respiratory rate, blood pressure, and age ≥ 65 years.

Ultimately, a DL model using initial chest radiographs predicted 30-day all-cause mortality in patients with CAP with AUC ranging from 0.77 to 0.80 in test cohorts from different institutions. Additionally, the model showed higher specificity (range, 61–69%) than the CURB-65 score (44–58%) at the same sensitivity (all p < .001).

An electronic supplement to this AJR accepted manuscript is available here.

North America’s first radiological society, the American Roentgen Ray Society (ARRS) remains dedicated to the advancement of medicine through the profession of medical imaging and its allied sciences. An international forum for progress in radiology since the discovery of the x-ray, ARRS maintains its mission of improving health through a community committed to advancing knowledge and skills with the world’s longest continuously published radiology journal—American Journal of Roentgenology—the ARRS Annual Meeting, InPractice magazine, topical symposia, myriad multimedia educational materials, as well as awarding scholarships via The Roentgen Fund®.

MEDIA CONTACT:

Logan K. Young, PIO

44211 Slatestone Court

Leesburg, VA 20176

lyoung@arrs.org

END


[Attachments] See images for this press release:
Deep-learning chest radiograph model predicts mortality for community-acquired pneumonia

ELSE PRESS RELEASES FROM THIS DATE:

Astrophysicists propose a new way of measuring cosmic expansion: lensed gravitational waves

Astrophysicists propose a new way of measuring cosmic expansion: lensed gravitational waves
2023-06-30
(Santa Barbara, Calif.) — The universe is expanding; we’ve had evidence of that for about a century. But just how quickly celestial objects are receding from each other is still up for debate.  It’s no small feat to measure the rate at which objects move away from each other across vast distances. Since the discovery of cosmic expansion, its rate has been measured and re-measured with increasing precision, with some of the latest values ranging from 67.4 up to 76.5 kilometers per second per megaparsec, which relates the recession velocity (in ...

Age prediction from human blood plasma using proteomic and small RNA data: A comparative analysis

Age prediction from human blood plasma using proteomic and small RNA data: A comparative analysis
2023-06-30
“[...] we see our work as an indication that combining different molecular data types could be a general strategy to improve future aging clocks.” BUFFALO, NY- June 30, 2023 – A new research paper was published on the cover of Aging (listed by MEDLINE/PubMed as "Aging (Albany NY)" and "Aging-US" by Web of Science) Volume 15, Issue 12, entitled, “Age prediction from human blood plasma using proteomic and small RNA data: a comparative analysis.” Aging clocks, built from comprehensive molecular data, have emerged as promising tools ...

New A.I. system can decode fruit fly behaviors. Why that’s ‘pivotal’ for future human genetics research

2023-06-30
How can you tell if a fruit fly is hungry? Ask a computer. While that may sound like a bad dad joke, it’s reality at Tulane University, where researchers have developed a new A.I. tool that can tell you if a fruit fly is hungry, sleepy or singing (yes, fruit flies sing).  Dubbed MAFDA (for Novel Machine-learning-based Automatic Fly-behavioral Detection and Annotation) the system uses cameras and a newly developed software to track and identify complex interactive behaviors of individual flies within a larger group. This allows researchers to compare and contrast the behaviors of fruit flies with different genetic backgrounds. For more than a century, ...

Breast cancer by age: Study reveals early mutations that predict patient outcomes

Breast cancer by age: Study reveals early mutations that predict patient outcomes
2023-06-30
LA JOLLA, CALIF. – June 30, 2023 – A study led by researchers at Sanford Burnham Prebys has found that in young women, certain genetic mutations are associated with treatment-resistant breast cancer. These mutations are not linked to treatment-resistant breast cancer in older women. The findings, published in the journal Science Advances, could help improve precision medicine and suggest a brand-new way of classifying breast cancer. “It’s well established that as you get older, you’re more likely to develop cancer. But we’re finding that this may not be true for all cancers depending on a person’s genetic makeup,” ...

Displays controlled by flexible fins and liquid droplets more versatile, efficient than LED screens

Displays controlled by flexible fins and liquid droplets more versatile, efficient than LED screens
2023-06-30
CHAMPAIGN, Ill. — Flexible displays that can change color, convey information and even send veiled messages via infrared radiation are now possible, thanks to new research from the University of Illinois Urbana-Champaign. Engineers inspired by the morphing skins of animals like chameleons and octopuses have developed capillary-controlled robotic flapping fins to create switchable optical and infrared light multipixel displays that are 1,000 times more energy efficient than light-emitting devices. The new study led by mechanical science and engineering professor Sameh Tawfick demonstrates ...

CU Anschutz researchers identify unique cell receptor, potential for new therapies

2023-06-30
AURORA, Colo. (June 30, 2023) – Researchers from the University of Colorado Anschutz Medical Campus have identified a potential new immune checkpoint receptor that could lead to treatments for diseases such as lung and bowel cancer and autoimmune conditions including IBD. The study, published today in Science Immunology, examines a family of 13 receptors, or proteins that transmit signals for cells to follow, called killer cell immunoglobulin-like receptors (KIR). Of the 13 receptors, one is unique in that it has not readily been observed on immune cells of ...

A new bacterial blueprint to aid in the war on antibiotic resistance

2023-06-30
A team of scientists from around the globe, including those from Trinity College Dublin, has gained high-res structural insights into a key bacterial enzyme, which may help chemists design new drugs to inhibit it and thus suppress disease-causing bacteria. Their work is important as fears continue to grow around rising rates of antibiotic resistance.  The scientists, led by Martin Caffrey, Fellow Emeritus in Trinity’s School of Medicine and School of Biochemistry and Immunology, used next-gen X-ray crystallography and single particle cryo-electron microscopy ...

Climate disasters, traumatic events have long-term impacts on youths' academics

2023-06-30
UNIVERSITY PARK, Pa. — Experiencing traumatic events such as natural disasters may have long-term consequences for the academic progress and future food security of youth — a problem researchers said could worsen with the increased frequency of extreme weather events due to climate change. In a study using data from Peru, researchers from Penn State’s College of Agricultural Sciences found that being exposed to a greater number of traumatic events or “shocks,” such as a natural disaster or loss of family income, in early ...

Researchers demonstrate single-molecule electronic "switch" using ladder-like molecules

2023-06-30
Researchers have demonstrated a new material for single-molecule electronic switches, which can effectively vary current at the nanoscale in response to external stimuli. The material for this molecular switch has a unique structure created by locking a linear molecular backbone into a ladder-type structure. A new study finds that the ladder-type molecular structure greatly enhances the stability of the material, making it highly promising for use in single-molecule electronics applications. Reported in the journal Chem, the study shows that the ladder-type molecule serves as a robust and reversible molecular switch over a wide range of conductivity levels and different molecular ...

Can bone-strengthening exercises and/or drugs reduce fracture risk when older adults lose weight?

2023-06-30
A $7 million study beginning this summer at Wake Forest University and Wake Forest University School of Medicine will help determine whether a combination of resistance training plus bone-strengthening exercises and/or osteoporosis medication use can help older adults safely lose weight without sacrificing bone mass. That paradox – that shedding pounds can help stave off heart disease and diabetes while increasing bone loss and subsequent fracture risk – has been a focus of Wake Forest researcher Kristen Beavers for about a decade.  Her previous research ...

LAST 30 PRESS RELEASES:

Urban fungi show signs of thermal adaptation

How to identify and prevent fraudulent participants in health research

Parents' attachment style may be linked with risk of parental burnout, especially when associated with difficulty in understanding and identifying their emotions

Abnormal repetitive behaviors in mice are associated with oxidative stress

Double disadvantage hurts more than twice as much

Paradox of rotating turbulence finally tamed with world-class ‘hurricane-in-a-lab’

Brain pathway may fuel both aggression, self-harm

Study: Macrophage “bodyguard” disruptors could change breast cancer treatment by helping to overcome endocrine resistance

New study reveals southern ocean’s winter CO₂ outgassing underestimated by 40%

U of A-led team discovers large ritual constructions by early Mesoamericans

MIT study finds targets for a new tuberculosis vaccine

Kono awarded American Physical Society’s Isakson Prize

Scripps Research team identifies sugar molecules that trigger placental formation

ITU at COP30: Driving Green Digital Action for a sustainable future

Want to be more persuasive? Talk with your hands, UBC study finds

Mount Sinai health system to roll out Microsoft Dragon copilot

Scientists map how the brain develops – and how it resolves inflammation

Triggering cell death in metastatic melanoma may pave the way for new cancer treatments

A path to safer painkillers – revealed by freezing opioids and their protein receptors in motion

Reducing reliance on corticosteroids with rituximab: renewed hope for adult-onset patients with relapsing nephrotic syndrome

Psilocybin outside the clinic – public health challenges of increasing publicity, accessibility, and use

Parent-teen sexual health communication and teens’ health information and service seeking

Two small changes, that may transform agriculture

New brain atlas offers unprecedented detail in MRI scans

Two main gene discovery methods reveal complementary aspects of biology

Blocking key protein triggers cancer cell self-destruction

Proposed all-climate battery design could unlock stability in extreme temps

Princeton’s new quantum chip built for scale

High risk of suicide after involuntary psychiatric care

From degradation to restoration: Remote sensing tracks Asia’s struggle for sustainable drylands

[Press-News.org] Deep-learning chest radiograph model predicts mortality for community-acquired pneumonia
A deep learning-based model using initial chest radiographs predicted 30-day mortality in patients with community-acquired pneumonia, improving upon the performance of an established risk prediction tool