Big Picture Makes Implementing Artificial Intelligence Smoother
When implementing artificial intelligence in a community hospital, it’s best to have buy-in from all stakeholders, not just a select few, according to an article published September 29, 2021, in the Journal of the American College of Radiology.
“Rather than invest right away in radiology AI algorithms that only benefit radiologists, Middlesex Health in Middletown, CT, elected to focus initially on AI applications outside of image interpretation, which would benefit all stakeholders in their community hospital setting,” reports Ridley.
Dr. Ravi Jain, Ph. D., offered this rationale for Middlesex Health’s (MH) AI implementation strategy. “‘Although radiologists at our institution saw AI as the future of the field, we were concerned that if the first deployment of AI in our health system was to assist the radiologists with image interpretation, the other stakeholders may not buy into the importance of AI and fully understand its utility,'” quoted Ridley.
Looking primarily to benefit patients, clinicians, and administrators, MH concentrated in the following areas, according to Ridley:
“Long acquisition times for PET/CT
Long acquisition times for MRI
Long wait times for the radiologist’s report on critical CT findings.”
Patients and administrators were pleased with the results. Fifty consecutive patients who received faster studies were surveyed and were unanimous in their preference for shorter scan times. Administrators found they saved more than 283 hours of scan time over traditional protocols over 21 months, according to Ridley.
Three-month validation of the software found no false-negative results, according to Ridley, who quoted Jain as writing, “‘Our goal of meeting the needs of all the stakeholders in the introduction of AI at our community hospital was achieved.'”