News | Coronavirus (COVID-19) | May 14, 2021

AI Tool Uses Chest X-ray to Differentiate Worst Cases of COVID-19

Chest X-ray from patient severely ill from COVID-19, showing (in white patches) infected tissue spread across the lungs. Image courtesy of Nature Publishing or npj Digital Medicine

Chest X-ray from patient severely ill from COVID-19, showing (in white patches) infected tissue spread across the lungs. Image courtesy of Nature Publishing or npj Digital Medicine

May 14, 2021 — Trained to see patterns by analyzing thousands of chest X-rays, a computer program predicted with up to 80 percent accuracy which COVID-19 patients would develop life-threatening complications within four days, a new study finds.

Developed by researchers at NYU Grossman School of Medicine, the program used several hundred gigabytes of data gleaned from 5,224 chest X-rays taken from 2,943 seriously ill patients infected with SARS-CoV-2, the virus behind the infections.

The authors of the study, publishing in the journal npj Digital Medicine online May 12, cited the "pressing need" for the ability to quickly predict which COVID-19 patients are likely to have lethal complications so that treatment resources can best be matched to those at increased risk. For reasons not yet fully understood, the health of some COVID-19 patients suddenly worsens, requiring intensive care, and increasing their chances of dying.

In a bid to address this need, the NYU Langone team fed not only X-ray information into their computer analysis, but also patients' age, race, and gender, along with several vital signs and laboratory test results, including weight, body temperature, and blood immune cell levels. Also factored into their mathematical models, which can learn from examples, were the need for a mechanical ventilator and whether each patient went on to survive (2,405) or die (538) from their infections.

Researchers then tested the predictive value of the software tool on 770 chest X-rays from 718 other patients admitted for COVID-19 through the emergency room at NYU Langone hospitals from March 3 to June 28, 2020. The computer program accurately predicted four out of five infected patients who required intensive care and mechanical ventilation and/or died within four days of admission.

"Emergency room physicians and radiologists need effective tools like our program to quickly identify those COVID-19 patients whose condition is most likely to deteriorate quickly so that health care providers can monitor them more closely and intervene earlier," says study co-lead investigator Farah Shamout, Ph.D., an assistant professor in computer engineering at New York University's campus in Abu Dhabi.

"We believe that our COVID-19 classification test represents the largest application of artificial intelligence in radiology to address some of the most urgent needs of patients and caregivers during the pandemic," said Yiqiu "Artie" Shen, MS, a doctoral student at the NYU Data Science Center.

Study senior investigator Krzysztof Geras, Ph.D., an assistant professor in the Department of Radiology at NYU Langone, says a major advantage to machine-intelligence programs such as theirs is that its accuracy can be tracked, updated and improved with more data. He says the team plans to add more patient information as it becomes available. He also says the team is evaluating what additional clinical test results could be used to improve their test model.

Geras says he hopes, as part of further research, to soon deploy the NYU COVID-19 classification test to emergency physicians and radiologists. In the interim, he is working with physicians to draft clinical guidelines for its use.

For more information: nyulangone.org

Related Content

Researchers have developed an artificial intelligence (AI)-based brain age prediction model to quantify deviations from a healthy brain-aging trajectory in patients with mild cognitive impairment, according to a study published in Radiology: Artificial Intelligence. The model has the potential to aid in early detection of cognitive impairment at an individual level.

Flowchart showing the framework of the brain age prediction model. A, The imaging data were split into training and test datasets. The training dataset consisted of structural magnetic resonance imaging data from 974 healthy individuals, whereas the test dataset included data from 2 groups, 231 healthy controls and 224 aMCI subjects. B, A Conventional Statistical Parametric Mapping structural preprocessing pipeline was used to generate GMV maps in the MNI space. C, The intensity values from the GMV maps were extracted and concatenated to create a feature matrix that was then cleaned and normalized. D, The best elastic net model was obtained by performing supervised learning on the training dataset. To optimize the hyperparameters, a grid search was performed. E, The test dataset was input into the trained model. An age was predicted for every participant included in the test dataset. The PAD scores were calculated by subtracting the participant's chronological age from his or her predicted age. aMCI = amnestic mild cognitive impairment, GMV = gray matter volume, MNI = Montreal Neurologic Institute, Dartel = Diffeomorphic Anatomic Registrations Through Exponentiated Lie Algebra, PAD = predicted age difference. Chart courtesy of Radiological Society of North America

News | Artificial Intelligence | June 23, 2021
June 23, 2021 — Researchers have developed an...
An example of a COVID-19 pneumonia of a chest CT scan. The COVID appears as white ground glass opacities (GGOs) in the lungs. Normal lungs on CT should appear black.

An example of a COVID-19 pneumonia of a chest CT scan. The COVID appears as white ground glass opacities (GGOs) in the lungs. Normal lungs on CT should appear black.

News | Coronavirus (COVID-19) | June 23, 2021
June 23, 2021 — The Radiological Society of North America (...
Led by a Michigan Medicine physician, the research team examined treatment outcomes over two years for patients who fractured their distal radius, the larger of two bones in the forearm. They found no one-size-fits all method for treating the fracture, which more than 85,000 Medicare beneficiaries sustain annually.

Getty Images

News | Radiology Imaging | June 23, 2021
June 23, 2021 — A decade-long...
According to a new study, by the Harvey L. Neiman Health Policy Institute and the American College of Radiology’s National Mammography Database Committee, the most influential radiologist characteristics impacting mammography interpretive performance were geography, breast sub-specialization, performance of diagnostic mammography, and performance of diagnostic ultrasound.

Getty Images

News | Breast Imaging | June 23, 2021
June 23, 2021 — According to a new ...
A phase III clinical trial has validated the effectiveness of the prostate-specific membrane antigen (PSMA)-targeted radiotracer 18F-DCFPyL in detecting and localizing recurrent prostate cancer.

Figure 1. Case example: A 54-year-old man with a history of RP+LND and a subsequent PSA of 1.25 ng/mL had no evidence of disease by baseline imaging. Piflufolastat F 18 (18F-DCFPyL)- PET/CT accurately detected biochemically recurrent prostate cancer with the PSMA PET/CT scan identifying positive left (left panel) and right peri-rectal lymph nodes (right panel).

News | Prostate Cancer | June 21, 2021
June 21, 2021 — A phase III clinica...
The Persona RF PREMIUM is an innovative radiography and fluoroscopy system designed for hospitals and medical centers of all sizes, providing real-time imaging for skeletal, digestive, urinary, respiratory, reproductive systems; and specific organs including the heart, lung and kidneys.
News | Digital Radiography (DR) | June 21, 2021
June 21, 2021 — FUJIFILM Medical Systems U.S.A., Inc., a leading provider of diagnostic imaging and medical informati
SNMMI's Image of the Year is a detailed depiction of areas of cognitive impairment, neurological symptoms and comparison of impairment over a six-month time frame

Figure 1. A: COVID-19-related spatial covariance pattern of cerebral glucose metabolism overlaid onto an MRI template. Voxels with negative region weights are color-coded in cool colors, and regions with positive region weights in hot colors. B: Association between the expression of COVID-19-related covariance pattern and the Montreal Cognitive Assessment (MoCA) score adjusted for years of education. Each dot represents individual patient. C: Results of a statistical parametric mapping analysis. Upper row illustrates regions that show significant increases of normalized FDG uptake in COVID-19 patients at 6-months follow-up compared to the subacute stage (paired t test, p < 0.01, false discovery rate-corrected). Bottom row depicts regions that still show significant decreases of normalized FDG uptake in COVID-19 patients at 6-months follow-up compared to the age-matched control cohort at an exploratory statistical threshold (two-sample t test, p < 0.005). Image Credit: G Blazhenets et al., Department of Nuclear Medicine, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg

News | PET Imaging | June 16, 2021
June 16, 2021 — The effects of COVID-19 on the b
The prevalence of genetic mutations associated with breast cancer in Black and white women is the same, according to a new JAMA Oncology study of nearly 30,000 patients led by researchers in the Basser Center for BRCA at the Abramson Cancer Center.

Getty Images

News | Women's Health | June 15, 2021
June 15, 2021 — The prevalence of genetic mutations associated with breast cancer in Black and white women is the sam