Decision Support: Canadian Study Finds Issues

Article

You can give doctors decision support advice, but you can't make them take it, according to a new study in the April issue of the Journal of the American College of Radiology.

You can give doctors decision support advice, but you can't make them take it, according to a new study in the April issue of the Journal of the American College of Radiology. The study followed the implementation of decision support software system and computerized order entry at the Children's Hospital in Winnipeg. The guidelines were from the pediatric section of the Canadian Association of Radiologists (CAR).

Doctors admitting to blatantly cheating the system and ignoring advice. It's not just a matter of being head-strong, though. The study found a host of implementation issues leading to the physicians' low system acceptance.

Decision support systems have become more popular due to questions about overutilization and inappropriate imaging. The researchers noted that up to one-third of diagnostic imaging studies are thought to be partially or completely inappropriate. And there are concerns about increased radiation exposure, especially in children (see DI article on the increase of emergency room CT scans in children in the U.S. ). One way to combat this is by mandating preauthorization for high utilizers and another way is through physician education through decision support software.

During the 14 months that the decision support guidelines were studied (from July 2006 to August 2007), physicians placed 8,757 orders. Of those, only 1,678 (19.2 percent) were found to have had relevant guidelines, and 957 (10.9 percent) were inappropriate, according to those guidelines. The system suggesting cancelling the imaging order 77 percent of the time (737 cases) and changing the order to another modality in 23 percent (220 cases) for cases. The system tagged 4 percent of the total orders (367 cases) as duplicative.

Researchers found a low rate of physicians following the decision support advice - only 19 cases (2 percent) for orders considered inappropriate. As for the duplicate order advice, 11 percent of the physicians (40 of 367) cancelled their imaging as a result. Advice was followed significantly more for ultrasound than X-ray, but there was no difference for other modalities.

Researchers found a host of reasons for the low acceptance rate of decision support, ranging from implementation to software issues to the timing of the advice (doctors already made up their minds about the imaging before ordering it). Importantly, while some physicians found the decision support interesting or informative, most did not find it useful, calling it irrelevant, too generic, or a "nuisance." Some even said they were "blatantly cheating" the system by learning how to avoid boxes that gave prompts.

The researchers concluded that it's important to ensure the timing of the implementation, and also to integrate it into the existing patient information system. The lack of complete patient data and using only a subset of CAR guidelines affected the results.

Recent Videos
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Related Content
© 2025 MJH Life Sciences

All rights reserved.