Not all radiologists adhere to practice guidelines that direct providers how to respond to the presence of pulmonary nodules.
A follow-up recommendation from a radiologist in response to a pulmonary nodule is not necessarily guaranteed. A new study shows there is widespread variation in whether providers make this call.
In a new study published Feb. 7 in the Journal of the American College of Radiology, investigators from Brigham and Women’s Hospital showed that radiologists do not always follow the practice guidelines that are intended to instruct them on how to respond when they detect pulmonary nodules.
“Unwarranted variation for pulmonary nodules could have significant downstream implication on not only frequency of repeat imaging, but overall medical costs and quality of patient care,” wrote the team led by Neena Kapoor, M.D., quality of patient safety officer with Brigham and Women’s radiology department. “How to alter radiologist behavior and reduce variation in reporting of follow-up recommendations is a challenging problem that likely requires multiple interventions and stake holder engagement.”
In reaching this conclusion, Kapoor’s team examined 142,001 chest and abdominal reports from its abdominal, thoracic, and emergency radiology sub-specialty divisions between Jan. 1, 2016, to Dec. 31, 2018. Using natural language processing, they identified 24,512 pulmonary nodule reports that did not end with a lung cancer diagnosis.
Among the reports they analyzed, 20 percent – 4,939 reports – included follow-up recommendations for pulmonary nodules. These reports came mainly from chest CTs (76 percent) and outpatient environments (63 percent), and thoracic radiologists assessed nearly two-thirds (64 percent).
According to their investigation, the team found that male patients and abdominal CTs were less likely to have a follow-up recommendation for a pulmonary nodule. However, older patients had higher rates of follow-up recommendations. In addition, inpatient and emergency department exams, as well as exams where a trainee is present, are more likely to result in a recommendation.
All told, the team said, they identified a 4.3-fold difference between radiologists in the probability that they would make a pulmonary nodule follow-up recommendation. However, they stopped short of drilling down on why these differences exist.
“Our work serves as a first step for future work to quantify the magnitude of variability in follow-up recommendations for pulmonary nodules,” they said. “Further studies will need to determine the downstream implications of variation in follow-up recommendations, including the clinical appropriateness of radiologist recommendations, variability in length of follow-up or imaging modalities used, and downstream imaging costs and quality of care.”
For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter here.
Photon-Counting Computed Tomography: Eleven Takeaways from a New Literature Review
May 27th 2025In a review of 155 studies, researchers examined the capabilities of photon-counting computed tomography (PCCT) for enhanced accuracy, tissue characterization, artifact reduction and reduced radiation dosing across thoracic, abdominal, and cardiothoracic imaging applications.
Can AI Predict Future Lung Cancer Risk from a Single CT Scan?
May 19th 2025In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.