When used alongside nurse coordinators, natural language processing (NLP) systems present a cost-effective means of increasing radiologist-recommended follow-up adherence among patients, leading to significantly increased revenue in radiology departments.
A new paper published in Current Problems in Diagnostic Radiology details how a team at the University of California utilized a hybrid system consisting of a quality coordinator and NLP software to bring in more than $60,000 in additional revenue from follow-up imaging alone. The team used special NLP software to identify radiology reports with follow-up imaging recommendations and refer them to a quality nurse who would then single out any incomplete cases and communicate the issue with referring providers and patients.
Corresponding author of the paper Bradley Roth from the Department of Radiological Sciences at the university, and colleagues suggested that hybrid systems similar to theirs can improve patient care while simultaneously turning a profit.
“The use of a hybrid human-AI system can prevent potential drops in communication and can assist in the coordination of follow-up care, while easing the burden of alert fatigue on referring providers,” the authors noted, adding that this cost-effective system also poses potential for reducing the risk of malpractice litigation.
To better understand how the system would affect costs, revenue and follow-up adherence, the team looked at data derived from reports generated at their institution between January 2020 and April 2021.
The NLP software (mPower Follow-Up Recommendation Algorithm from Nuance Communications) flagged 3,011 patients as not having received timely follow-up imaging, 427 of which required a nurse coordinator to place the orders. The team estimated the follow-up imaging of these patients would have resulted in an additional $62,937 in revenue based on 2020-2021 Medicare reimbursement rates. This figure was calculated as a higher amount than that of the associated personnel costs, and it likely significantly underestimates the true revenue derived from follow-up imaging, the team noted.
“Our revenue assessment was made only on the patients that required new imaging orders to be placed with our system's help,” the group explained. “We excluded all patients who had preexisting imaging orders but needed significant follow-up help from our quality and safety nurse to schedule and complete their imaging exams. This conservative methodology was least prone to measurement bias.”
Even if the hybrid system did not produce additional revenue, the team suggested that its patient care benefits make its use a worthwhile investment.
“... given the potential patient safety and medicolegal liability of potential missed follow-ups, the authors believe that, even with a net loss, this system would pose great benefits to most healthcare systems,” the group wrote.
The study abstract is available here.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She joined Innovate Healthcare in 2021 and has since put her unique expertise to use in her editorial role with Health Imaging.