New real-world evidence supports the use of AI in lung cancer screening
Radiologists spot significantly more suspicious lung nodules with the help of artificial intelligence support, a new study suggests.
New data shared in the American Journal of Roentgenology detail a comparison of interpretation times and detection rates of radiologists both with and without the help of AI. Though the study of AI in lung cancer screening is not new, prior retrospective research has made it challenging for to determine the real-world impact of such tools. This latest study addresses this shortcoming by offering prospective insight into how an AI-based lung nodule detection tool performs in clinical practice for asymptomatic patients undergoing lung cancer screening.
The prospective trial included consecutive individuals who underwent low-dose CT of the chest during a self-initiated checkup between May and September of 2025. Patients were randomized to one of two groups—those who received AI assistance and others whose exams were read by a radiologist alone. Researchers aimed to assess how AI support impacted interpretation times, with a secondary analysis focusing on nodule detection rates and subsequent follow-up recommendations.
There were 911 patients who underwent LDCT during the trial (517 men and 394 women, at an average age of 67 years). Interpretation times were similar between both groups, with the intervention group (AI-assisted) taking an average of 15 seconds longer to evaluate scans compared to the control arm. AI support, however, resulted in a significant increase in nodule detection; AI identified more Lung-RADS-positive nodules (and more nodules in general) and produced double the amount of imaging follow-up recommendations than the control group.
“Use of an AI-based nodule evaluation tool integrated into PACS during real-world clinical workflows was not associated with a significant difference in interpretation times,” Jin Mo Goo, MD, PhD, with the department of radiology at Seoul National University Hospital, and colleagues noted. “However, the tool was associated with significantly greater detection of clinically actionable nodules.”
The team suggested their findings provide “pragmatic evidence” of AI’s impact in real-world cancer screening.
Read more here.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.