(Press-News.org) OAK BROOK, Ill. - A deep learning algorithm accurately predicts the risk of death from cardiovascular disease using information from low-dose CT exams performed for lung cancer screening, according to a study published in Radiology: Cardiothoracic Imaging.
Cardiovascular disease is the leading cause of mortality worldwide. It even outpaces lung cancer as the leading cause of death in heavy smokers.
Low-dose CT lung scans are used to screen for lung cancer in high-risk people such as heavy smokers. These CT scans also provide an opportunity to screen for cardiovascular disease by extracting information about calcification in the heart and aorta. The presence of calcium in these areas is linked with the buildup of plaque and is a strong predictor for cardiovascular disease mortality, heart attacks and strokes.
Previous studies have used information extracted from CT images as well as other risk factors, such as cholesterol levels and blood pressure, and self-reported clinical data, such as history of illness.
For the new study, researchers tested a faster, automated method that can predict five-year cardiovascular disease mortality with only minimal extra workload. The method draws upon the power of deep learning, an advanced type of artificial intelligence in which the computer algorithm essentially learns from the images the important features for mortality prediction.
Using data from 4,451 participants, median age 61 years, who underwent low-dose CT over a two-year period in the National Lung Screening Trial, the researchers trained the method to quantify six types of vascular calcification. They then tested the method on data from 1,113 participants.
The prediction model using calcium scores outperformed the baseline model that used only self-reported participant characteristics, such as age, history of smoking, and history of illness.
The method works in two stages, according to study lead author Bob D. de Vos, Ph.D., from Amsterdam University Medical Center in Amsterdam and the Image Sciences Institute, University Medical Center Utrecht, in Utrecht, the Netherlands. The first stage determines the amount and location of arterial calcification in the coronary arteries and the aorta using deep learning. The second stage uses a more conventional statistical approach for mortality prediction. The second stage also indicates which features are most predictive for five-year mortality.
"The analysis shows we found predictors that are typically not described in a literature, possibly because we performed analysis in lung cancer screening participants who are already at high risk of cardiovascular disease from a history of heavy smoking and the presence of extensive arterial calcification," Dr. de Vos said.
The method could easily be integrated into lung cancer screening, Dr. de Vos said. It does not require any special equipment and would not add time to the exam.
"The method uses only image information, it is fully automatic, and it is fast," Dr. de Vos said. "The method obtains calcium scores in a complete chest CT in less than half a second. This means that the method should be easy to implement in routine patient work ups and screening."
Most importantly, the method could help identify people in a population of heavy smokers who might be at increased risk of death from cardiovascular disease-related causes.
"Lung screening studies show that heavy smokers die from cardiovascular disease as much as from lung cancer," Dr. de Vos said. "But we also see that some people with very high calcium scores survive, while others with low scores do suffer from major cardiac events. The work offers a direction for future research to precisely pinpoint which calcifications are dangerous."
The researchers have developed a number of methods for automatic calcium scoring that can be applied to a wide variety of data. They are now working toward a calcium scoring method that accurately detects arterial calcification in low-quality data, like data affected by cardiac motion, low image resolution or high noise levels.
"We developed a method, for example, that can detect coronary calcifications even when the lesions are below the clinically used threshold," Dr. de Vos said. "This way, we hope to increase the reproducibility of calcium scoring and enable more accurate prediction."
The United States Preventive Services Task Force (USPSTF) recently expanded its recommendation for low-dose CT lung cancer screening to include high-risk individuals, 50 to 80 years of age, who have a 20-pack-year or more history of smoking and are either current smokers or former smokers who have quit within the last 15 years, facilitating screening access for a larger and more diverse population. Read more in RSNA News.
INFORMATION:
"Deep Learning-Quantified Calcium Scores for Automatic Cardiovascular Mortality Prediction at Lung Screening Low-Dose CT." Collaborating with Dr. de Vos were Nikolas Lessmann, Ph.D., Pim A. de Jong, M.D., Ph.D., and Ivana Išgum, Ph.D.
Radiology: Cardiothoracic Imaging is edited by Suhny Abbara, M.D., University of Texas Southwestern Medical Center, Dallas, and owned and published by the Radiological Society of North America, Inc.
RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Ill. (RSNA.org)
For patient-friendly information on lung cancer screening, visit RadiologyInfo.org.
Key takeaways
Pancreatic, liver, bile duct, and stomach cancer operations are inherently complex and initially often take place at large cancer centers where surgical teams perform a large volume of procedures.
Readmission to a different hospital from where patients had these operations initially performed markedly increases death risk.
There are ways to address care fragmentation with newly identified risk factors for readmission; cancer hospitals should seek to determine safe sites of care for readmissions after these types of operations.
CHICAGO: New research reveals that 28 percent of patients who are readmitted ...
Patients who are overweight or obese have more severe COVID-19 and are highly likely to require invasive respiratory support, according to a new international study.
The research, led by the Murdoch Children's Research Institute (MCRI) and The University of Queensland and published in Diabetes Care, found obese or overweight patients are at high risk for having worse COVID-19 outcomes. They are also more likely to require oxygen and invasive mechanical ventilation compared to those with a healthy weight.
MCRI researcher Dr Danielle Longmore said the findings, which highlighted the relationship between obesity and increased COVID-19 disease burden, showed the need to urgently introduce strategies to address ...
https://www.sciencedirect.com/journal/acta-pharmaceutica-sinica-b/vol/11/issue/3
The Journal of the Institute of Materia Medica, the Chinese Academy of Medical Sciences and the Chinese Pharmaceutical Association, Acta Pharmaceutica Sinica B (APSB) is a monthly journal, in English, which publishes significant original research articles, rapid communications and high quality reviews of recent advances in all areas of pharmaceutical sciences -- including pharmacology, pharmaceutics, medicinal chemistry, natural products, pharmacognosy, pharmaceutical analysis and pharmacokinetics.
Featured papers in this issue are:
Isorhapontigenin protects against doxorubicin-induced ...
Guangzhou, April 8, 2021: New journal BIO Integration (BIOI) publishes its fifth issue, volume 2, issue 1. BIOI is a peer-reviewed, open access, international journal, which is dedicated to spreading multidisciplinary views driving the advancement of modern medicine. Aimed at bridging the gap between the laboratory, clinic, and biotechnology industries, it will offer a cross-disciplinary platform devoted to communicating advances in the biomedical research field and offering insights into different areas of life science, to encourage cooperation and exchange among scientists, clinical researchers, and health care providers.
The issue contains an editorial, two mini review articles, two opinion articles and an interview offering ...
The inner surface of blood vessels is lined by a wafer-thin layer of cells known as the endothelium, which forms a crucial barrier between blood and the surrounding tissue. The single-layered cell structure promotes the exchange of oxygen and nutrients, while simultaneously preventing the uncontrolled leakage of blood components. Only when the metabolic needs of the surrounding tissue increase, e.g., during growth, wound healing or tumor development, do endothelial cells abandon this stable cell association in order to divide and form new blood vessels. The signals that trigger this activation have been ...
Detecting hidden genetic defects by applying an existing method to an existing datasets. Researchers at Radboud university medical center have succeeded: they showed that the 'Expansion Hunter' method can detect errors in the DNA that lead to repeat expansion diseases, such as the movement disorder ataxia. This result provides guidance to fellow researchers worldwide on how to use this method to diagnose patients with genetic disorders.
With current diagnostic technology for genetic disorders, it is possible to map all 20,000 genes in our DNA at once. Doctors are increasingly opting for this so-called exome technique: it is widely applicable and increasingly provides molecular diagnoses. ...
High intensity interval training has become increasingly popular as it's a quick and effective way to improve health. This is all the more important as countries around the world emerge from lockdowns due to coronavirus and are looking for quick and easy way to exercise again.
Recently, researchers have been studying whether shorter variations of HIIT, involving as little as 4-min of high intensity exercise per session (excluding a warm up and cool down), also improve health.
A new review paper published in the Journal of Physiology collates a decade's worth of research ...
Words categorize the semantic fields they refer to in ways that maximize communication accuracy while minimizing complexity. Recent studies have shown that human languages are optimally balanced between accuracy and complexity. For example, many languages have a word that denotes the colour red, but no language has individual words to distinguish ten different shades of the colour. These additional words would complicate the vocabulary and rarely would they be useful to achieve precise communication.
A study published on 23 March in the journal Proceedings of the ...
The corona pandemic has had a major impact on the Nordic news media. At the same time as advertising revenues have fallen drastically, interest among the audience for professional news coverage has increased, according to a new report from Nordicom at the University of Gothenburg. Several Nordic media companies have also reported record sales of digital subscriptions as a result of the pandemic.
Covid-19 swept over the Nordic region and the rest of the world with full force in the spring of 2020. A year later, the pandemic still has the world in a strong grip. However, both the health-related ...
ITHACA, N.Y. - Millions of people donate billions of dollars' worth of their time to citizen-science projects each year. While these efforts have broadened our understanding of everything from birds to bees to bracken ferns, rarely has citizen-science data informed policy at the highest levels of government. But that may be changing.
One of the world's largest citizen-science efforts, the Cornell Lab of Ornithology's eBird, is now helping the federal government streamline and refine its process for assessing eagle populations and informing eagle management.
New research out this week in the Journal of ...
