Clarity in recommendations leads to a malignant diagnosis in a substantial number of cases.
Strong, specific follow-up recommendations by radiologists in FDG-PET/CT reports result in higher compliance from referring physicians, according to a study in theJournal of the American College of Radiology.
Researchers from the Netherlands performed a retrospective study to investigate how frequently and when referring physicians follow the recommendation in an 18F-fluoro-2-deoxy-D-glucose PET/CT (FDG-PET/CT) report and to determine the diagnostic yield of these recommendations.
The researchers obtained data from 2,496 clinical FDG-PET/CT scans performed at a tertiary care academic medical center in a 1.5-year period. They extracted the following variables from each report that contained a recommendation:
• Patient age
• Patient gender
• Hospital status (inpatient versus outpatient)
• Indication for FDG-PET/CT scanning
• Descriptive clarity of the recommendation
• Type of recommendation (additional imaging versus other)
• Compliance of the referring physician with the recommendation
The results showed the 2,496 FDG-PET/CT reports contained 193 recommendations (7.7 percent), of which 120 (62.2 percent) were followed by the referring physicians. Only the strength of the recommendation (strong versus weak wording) was significantly associated with the referring physicians’ compliance with the recommendations in the FDG-PET/CT report. Of 120 recommendations that were followed, 21 (17.5 percent) led to a malignancy diagnosis; 3 of the 73 (7.2 percent) recommendations that were not followed proved to have led to a malignancy diagnosis based on follow-up examinations not related to the recommendation; these proportions were significantly different.
The researchers concluded that recommendations for additional radiological and nonradiological examinations in clinical FDG-PET/CT reports were relatively low but recommendations are mostly followed and lead to a malignant diagnosis in a substantial number of cases. Compliance of the referring physician was influenced by the strength of the recommendation.
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
The Reading Room Podcast: Emerging Trends in the Radiology Workforce
February 11th 2022Richard Duszak, MD, and Mina Makary, MD, discuss a number of issues, ranging from demographic trends and NPRPs to physician burnout and medical student recruitment, that figure to impact the radiology workforce now and in the near future.