MIT study finds decision support software trims imaging exams

Clinical decision support software may play a key role in helping physicians make decisions about expensive imaging exams, reducing their use.

A new study from the Massachusetts Institute of Technology finds that decision-support software could curb the overuse of costly diagnostic imaging tests by about 6 percent. The study, conducted by MIT’s Sloan School of Management, is believed to be the first large-scale randomized evaluation of the impact of CDS ; results of the initiative were published in the journal PLOS ONE.

The study is important for a couple reasons. First, the Centers for Medicare and Medicaid Services will implement new regulations next year that require imaging orders to be accompanied by a CDS recommendation in order for them to be reimbursed by Medicare. Second, there’s growing industry concerns about both the cost of the examinations and potential harmful physical effects from exposing patients to radiation from unnecessary procedures.

Also See: AI reduces time needed to generate radiation therapy plans

"There is a lot of debate about the health risks and high costs that stem from the overuse of potentially inappropriate tests," says Joseph Doyle, the Erwin H. Schell Professor of Management and Applied Economics at the MIT Sloan School of Management, and one of the authors of the study. "Our research shows that technology can improve healthcare delivery by helping physicians make the right decisions about which diagnostic scans to use when."



In conducting the study, physicians and other healthcare providers were randomly selected to get CDS software to guide imaging decisions. The decision support provided information about whether a test ordered for a patient was appropriate based on guidelines from the American College of Radiology.

The researchers conducted a year-long trial of CDS software at Aurora Health Care, the largest healthcare system in Wisconsin, involving 3,511 healthcare providers, half of whom were randomly assigned to receive the tool. The control group continued to order images as they had prior to when the trial began.

The study found that the CDS application helped reduce targeted scans by about 6 percent, compared with exams ordered by the control group. CT scans—the most common high-cost imaging modality, which also carries the greatest concerns about over-ordering—represented four-fifths of the overall reduction in targeted scans.

While the software changed the nature of image orders, it did not change the number of images ordered overall. The effects persisted over time, suggesting that this type of alert can continue to affect ordering even with concerns about alert fatigue more generally.

With the impending wave of digital health tools intended to guide physician decision-making, randomizing the rollout of these tools provides a golden opportunity to test how doctors respond to the information, the researchers contend.

"Our study was meant to understand whether software alone has potential to help doctors improve their decision-making around ordering these expensive and often risky tests because such an intervention is easily scaled," Doyle says. "This is especially the case for diagnostic testing, given the imminent mandate that CDS be used for high-cost imaging to be eligible for Medicare reimbursement. Further understanding of the most effective ways to employ the technology beyond simply showing the information about the guidelines remains an important area for future research."