According to new research, artificial intelligence (AI) is more than twice as good than radiologists alone at screening patients for lung cancer.
In a real-world context, machine learning-based software improved the detection of lung nodules on chest X-rays substantially.
Lung Nodules Are Primary Finding Of Lung Cancer
The approach is more sensitive and less prone to overlook cases that require rapid attention. It has the potential to enhance survival rates for one of the disease’s deadliest forms.
Infections frequently cause abnormal growth. They can be a symptom of malignancy in some circumstances.
It comes as new research in the United Kingdom discovered that AI technology can detect bowel cancer instances that humans overlook. Cancers of the lungs and bowel are among the most frequent in the United States.
Lung nodules, which are abnormal growths on the lungs, are highly frequent and usually develop as a result of previous lung infections. They can be a symptom of lung cancer in rare cases. Chest X-rays are a standard screening approach for finding lung nodules. When radiologists are dealing with a huge volume of cases, AI can be a significant tool in assisting with the identification of lung nodules.
“Detecting lung nodules, a primary finding of lung cancer, is one of the crucial tasks in chest X-rays,” said study co-author Jin Mo Goo, M.D., Ph.D., of Korea’s Department of Radiology. “Many studies have suggested that AI-based computer-aided detection software can improve radiologists’ performance, but it is not widely used.”
Researchers enrolled 10,476 individuals with an average age of 59 who received chest X-rays at a health screening center between June 2020 and December 2021 to determine the actual effect of AI in clinical practice.
Patients filled out a self-reported health questionnaire to determine baseline variables such as age, gender, smoking status, and a history of lung cancer. 11% of the patients were current or previous smokers.
Actionable nodules were defined as solid nodules with diameters greater than 8 millimeters or subsolid nodules with a solid component greater than 6 millimeters, implying that the nodule required follow-up in accordance with lung cancer screening guidelines.
Read more: Mental health issues linked to absenteeism of children
AI Improves Lung Nodule Detection On X-Ray
Lung nodules were found in 2% of patients. The identification rate for actionable lung nodules on chest X-rays was greater with AI support (0.59%) than without AI assistance (0.25%). The false-referral rates did not differ between the AI and non-AI-interpreted groups.
While older age and a history of lung cancer or tuberculosis were related with good reports, these and other health variables had no effect on the AI system’s performance. This shows that AI may be effective in a variety of populations, including people with damaged or surgical lungs.
The researchers intend to do a similar study utilizing chest CT to identify clinical outcomes and workflow efficiency.
Read more: Child Tax Credit 2023: How much money you can receive, how to apply?