Artificial intelligence (AI) is more than twice as good as radiologists alone at screening patients for lung cancer, new research has found.
In a real-world setting, machine learning-based software has significantly improved the identification of lung nodules on chest X-rays.
The technique is more sensitive and less likely to miss cases that require immediate treatment. This could improve survival rates for one of the deadliest forms of the disease.
The abnormal growths usually form after infection. In some cases, they can be a sign of cancer.
It comes after a new study in the UK found that AI technology can also detect cases of colon cancer that humans miss. Lung and colon cancer are among the most common cancers in the United States.
The above scan is from a patient in the study. On the left is the scan seen by doctors with an arrow pointing to the lung nodule diagnosed with cancer. On the right is the scan entered into the AI with the green dot over the same lung nodule. The dot indicates that the device has detected a lump that needs to be evaluated for cancer
Small WORMS can be used to detect lung cancer cells in urine and saliva
Researchers at Myongji University in Korea conducted laboratory experiments on roundworms and found that they navigate cancer cells by following an odor trail.
co-author dr. Jin Mo Goo of Seoul National University Hospital said, “The detection of pulmonary nodules, a primary finding of lung cancer, is one of the critical tasks of chest X-rays.
“Many studies suggest that AI-based computerized sensor software can improve radiologist performance, but it is not widely adopted.”
Lung cancer is too often diagnosed after it has spread because there are few early symptoms.
An estimated 238,340 people will be diagnosed with lung cancer in the U.S. in 2023, although that trend is declining — likely due to fewer people smoking.
About 127,070 Americans die from the disease each year.
For the study, researchers enrolled 10,476 patients who underwent chest X-rays at a screening center between June 2020 and December 2021.
Dr. Goo said, “Because our study was conducted with a pragmatic approach, almost all enrolled participants were included, which is a true clinical setting.”
Age, gender and history of lung cancer were taken into account. One in nine (11 percent) was a current or former smoker.
Participants were randomly and equally divided into two groups – AI or non-AI. The X-rays of the first group were analyzed by one of three radiologists using AI, while those of the second group were interpreted without the technology.
Lung nodules requiring attention were detected 0.59 percent of the time using AI, compared to 0.25 percent of the others whose images were only reviewed by radiologists.
Overall, pulmonary nodules were identified in two percent of patients.
Dr. Goo said: “Our study provided strong evidence that AI can really help interpret chest X-rays.
“This allows breast diseases, especially lung cancer, to be detected earlier.”
The results, published in Radiology, also suggest that AI works consistently across populations — even in people with diseased or post-surgical lungs.
AI has already been shown to help predict several types of cancer, including breast cancer, as well as bowel disease, Alzheimer’s, heart attacks and dementia.
Source link
Crystal Leahy is an author and health journalist who writes for The Fashion Vibes. With a background in health and wellness, Crystal has a passion for helping people live their best lives through healthy habits and lifestyles.
