Pulmonary nodules are very common and typically form from previous lung infections. In rare cases, they can be a symptom of lung cancer. Artificial intelligence can be a powerful tool to help identify pulmonary nodules, especially when radiologists experience a high volume of cases.
“The detection of pulmonary nodules, the primary finding of lung cancer, is one of the key tasks in chest X-ray examination,” said study co-author Jin Mo Goo, MD, PhD, from the Department of Radiology at Seoul National University Hospital in Korea. . “Many studies suggest that AI-based computer-aided detection software can improve the performance of radiologists, but it is not widely used.”
To identify the real effect that AI has in clinical practice, the researchers included 10,476 patients with an average age of 59 who underwent a chest X-ray examination at a health screening center between June 2020 and December 2021.
“Because our study was conducted with a pragmatic approach, almost all enrolled participants were included, which is a real clinical setting,” said Dr. Goo.
Patients completed a self-reported health status questionnaire to identify baseline characteristics such as age, sex, smoking history, and history of lung cancer. Eleven percent of patients were current or former smokers.
Patients were randomly divided equally into two groups – AI or no AI. The X-rays of the first group were analyzed by radiologists with the help of AI, while the X-rays of the second group were interpreted without AI results.
Solid nodules with a diameter of either greater than 8 millimeters or subsolid nodules with a solid portion greater than 6 millimeters were identified as usable.
Age and other health characteristics did not affect the effectiveness of artificial intelligence
Pulmonary nodules were identified in 2% of patients. The analysis showed that the detection rate of functional pulmonary nodules on chest radiographs was higher with AI (0.59%) than without AI (0.25%). There were no differences in false referral rates between the AI ​​and non-AI interpreted groups.
While older age and a history of lung cancer or tuberculosis were associated with positive reports, these and other health characteristics did not affect the effectiveness of the AI ​​system. This suggests that AI can work consistently across different populations, including those with diseased or post-surgery lungs.
“Our study provided strong evidence that artificial intelligence can indeed help in chest X-ray interpretation. This will contribute to more effective identification of chest diseases, especially lung cancer, at an earlier stage,” said Dr. Goo. The researchers plan to conduct a similar study using chest CT, which will also determine clinical outcomes and the effectiveness of the workflow.
Read Now :<strong>7800 deaths in Turkey, Chinese earthquake rescue team arrives in Turkey</strong>
