Chest CT follow-ups recommended by radiologists following chest radiograph result in clinically relevant findings.
Recommendations by radiologists for chest CT evaluation of an abnormal finding on an outpatient chest radiographic examination result in a substantial number of clinically relevant findings, according to a new study published online in the journal Radiology.
Researchers from Harvard Medical School sought to evaluate the diagnostic yield of radiologist recommendations for additional imaging (RAIs) that were prompted by abnormalities detected by the reviewing radiologists.
“There has been a great deal of research on how radiologists recommend an imaging exam, but little on what comes out of the exams that they recommend,” study author Tarik K. Alkasab, MD, PhD, said in a release. “Prior studies were very broad, so in our study we tried to focus on a specific clinical scenario.”
A total of 29,138 outpatient chest radiographs obtained during 2008 were reviewed for recommendations for chest CT imaging within one year of the chest X-ray. The researchers found 2,996 (10.3%) of the chest radiographic examinations matched the initial text-based screen for recommendations. A manual review of the 2,996 reports found that 1,316 had recommendations for a chest CT examination, for a CT examination recommendation rate of 4.5%. “Individual CT recommendation rates for the 11 interpreting thoracic radiologists ranged from 2.5% to 8.7% (mean, 4.7% ± 2.0),” wrote the authors. “There was a trend toward lower recommendation rates in thoracic radiologists with more years of experience, but this was not statistically significant.”
Increasing patient age and a positive smoking history were associated with increased likelihood of a recommendation for chest CT examination, the researchers found. Of patients within this subset who met inclusion criteria, 65.4% (691 of 1,057) underwent a chest CT examination within the year after the index chest radiographic examination.
Also in this group of 691 patients, 56 (8.1%) had newly diagnosed, biopsy-proven malignancies that were detected.
“In this era of concern about radiation dose risk, these findings suggest that the extremely low predicted risk of radiation-induced cancer associated with a chest CT is orders of magnitude less than the potential clinical benefits,” study co-author H. Benjamin Harvey, MD, JD, said in the release. “If ordering physicians see a recommendation for chest CT, they need to ensure that the patient gets the recommended imaging.”
The researchers concluded that a radiologist recommendation for chest CT to evaluate an abnormal finding on an outpatient chest radiographic examination has a high yield of clinically relevant findings. However, more research is still needed, they noted.[[{"type":"media","view_mode":"media_crop","fid":"30603","attributes":{"alt":"Examples of lesions seen on chest radiograph images that prompted a recommendation for chest CT examination.","class":"media-image media-image-right","id":"media_crop_8305967599520","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"3213","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 549px; width: 400px; border-width: 0px; border-style: solid; margin: 1px; float: right;","title":"Examples of lesions seen on chest radiographic images that prompted a recommendation for chest CT examination and the corresponding abnormality on chest CT. Image courtesy of Radiology. © RSNA, 2014. ","typeof":"foaf:Image"}}]]
What is the Best Use of AI in CT Lung Cancer Screening?
April 18th 2025In comparison to radiologist assessment, the use of AI to pre-screen patients with low-dose CT lung cancer screening provided a 12 percent reduction in mean interpretation time with a slight increase in specificity and a slight decrease in the recall rate, according to new research.
Meta-Analysis Shows Merits of AI with CTA Detection of Coronary Artery Stenosis and Calcified Plaque
April 16th 2025Artificial intelligence demonstrated higher AUC, sensitivity, and specificity than radiologists for detecting coronary artery stenosis > 50 percent on computed tomography angiography (CTA), according to a new 17-study meta-analysis.
Can CT-Based AI Radiomics Enhance Prediction of Recurrence-Free Survival for Non-Metastatic ccRCC?
April 14th 2025In comparison to a model based on clinicopathological risk factors, a CT radiomics-based machine learning model offered greater than a 10 percent higher AUC for predicting five-year recurrence-free survival in patients with non-metastatic clear cell renal cell carcinoma (ccRCC).