Tuesday, May 11, 2021
Home Lead Story Researchers Develop Artificial Intelligence Tool in Chest X-Rays to Predict Long Term...

Researchers Develop Artificial Intelligence Tool in Chest X-Rays to Predict Long Term Mortality

Each image was paired with a key piece of data: Did the person die over a 12-year period?

Researchers have developed an Artificial Intelligence (AI)-powered tool that can harvest information in chest X-rays to predict long-term mortality.

The findings of this study, published in the journal JAMA Network Open, could help to identify patients most likely to benefit from screening and preventive medicine for heart disease, lung cancer and other conditions.

“This is a new way to extract prognostic information from everyday diagnostic tests,” said one of the researchers, Michael Lu, from Massachusetts General Hospital (MGH) of Harvard Medical School. “It’s information that’s already there that we’re not using, that could improve people’s health,” Lu said. Lu and his colleagues developed a convolutional neural network – an AI tool for analysing visual information – called CXR-risk.

artificial Intelligence
Next, Lu and colleagues tested CXR-risk using chest X-rays for 16,000 patients from two earlier clinical trials. Pixabay

It was trained by having the network analyse more than 85,000 chest X-rays from 42,000 participants who took part in an earlier clinical trial. Each image was paired with a key piece of data: Did the person die over a 12-year period? The goal was for CXR-risk to learn the features or combinations of features on a chest X-ray image that best predict health and mortality.

ALSO READ: Why Virtual Reality Headsets Failed to Create Craze Among Masses?

Next, Lu and colleagues tested CXR-risk using chest X-rays for 16,000 patients from two earlier clinical trials. They found that 53 per cent of people the neural network identified as “very high risk” died over 12 years, compared to fewer than four per cent of those that CXR-risk labeled as “very low risk.”

The study found that CXR-risk provided information that predicts long-term mortality, independent of radiologists’ readings of the x-rays and other factors, such as age and smoking status. Lu believes this new tool will be even more accurate when combined with other risk factors, such as genetics and smoking status. (IANS)

STAY CONNECTED

19,511FansLike
362FollowersFollow
1,773FollowersFollow

Most Popular

Knowledge Sharing Social Media Platform For Medical Students: MedBound

We've already been using major social networking sites for different purposes. Well, there are also some social networking sites that aren't to be missed...

Covid19 In India Brought Automation Technologies And IA To The Forefront

The Covid-19 pandemic has brought automation technologies to the forefront and the Intelligent Automation (IA) market in India is estimated to grow at a...

Corset: A Brief History

By- Khushi Bisht Corsets have existed for a very long time. It first originated in Italy and was brought to France in the 16th century...

Hybrid Work Is The Next Big Disruption In US Society

By Dora Mekouar Hybrid schedules could be the next monumental shift in the American workplace after last year's sudden move to remote work. More than 70%...

An Overview Of Bipolar Disorder

BY- JAYA CHOUDHARY Bipolar disorder, also known as bipolar depressive disorder, is a neurological disorder that causes mood and behavior changes. Bipolar disorder is characterized...

Cancer Immunotherapy Approach Targets Common Genetic Alteration

By Blake Jones Researchers have found a prototype for a new kind of immunotherapy for cancer. This therapy uses modified T-cells to target and attack...

Outlook Into Wellness Tourism Growth During Pandemic

The roller coaster ride that was 2020 brought the biggest dip in modern history, forcing individuals to adapt to major lifestyle changes while the...

Strengthen Your Immune System Against Foreign Pathogens

At the personal level, the fight against the Covid-19 virus begins with strong immunity. As the second wave turns out to be more alarming...

Recent Comments