Rereading CTs in EDs receiving a transfer patient may detect major discordance in interpretation, from RSNA 2016.
Routine over-reading of pre-transfer CT scans may be justified due to the substantial likelihood of a major discordance in interpretation that may impact the clinical management of patients, according to a study presented at RSNA 2016.
Researchers from Seattle, WA, performed a retrospective study to determine the concordance rate of CT interpretations of emergently transferred patients to a Level I trauma center. They reviewed outside CT scans of all adult patients who were transferred to the emergency department of a Level I trauma center from May 9, 2015 to June 9, 2015. A total of 628 scans from 327 transfers were reviewed. The patients were categorized as trauma or non-trauma transfers. The original imaging report was compared to the reviewer’s findings, and categorized as concordant or discordant. Discordant findings were rated as minor, moderate, or major. Major discordances were defined as having the potential to impact clinical management. Rates of each type of discordance and 95% confidence intervals (CIs) were calculated per transfer and per exam.
The results showed that there were 213 (65%) trauma transfers and 114 (35%) non-trauma transfers, corresponding to 490 trauma-related exams and 138 non-trauma exams. Of the 327 total transfers, there were 119 (36%) with any discordance and 56 (17%) with at least one major discordance. These major discordances were identified in 49 (23%) of the 213 trauma transfers and seven (6.1%) of the non-trauma transfers.
On a per exam basis, 59 of 628 (9.4%) total exams had a major discordance. There were 51 (10%) major discordances among the trauma-related exams and eight (5.8%) among the non-trauma exams.
The researchers concluded that there were major interpretive discrepancies in the CT scans of 17% of patients emergently transferred to a Level I trauma center, and that trauma transfer patients were significantly more likely to have a major discordance than non-trauma transfer patients.
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.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
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).
Could Lymph Node Distribution Patterns on CT Improve Staging for Colon Cancer?
April 11th 2025For patients with microsatellite instability-high colon cancer, distribution-based clinical lymph node staging (dCN) with computed tomography (CT) offered nearly double the accuracy rate of clinical lymph node staging in a recent study.