HomeTechnologyArtificial intelligenceAI boosts patient follow-up imaging compliance

AI boosts patient follow-up imaging compliance

The research group aimed to improve patient compliance rates for follow-up imaging recommendations by implementing a natural language processing (NLP) algorithm and tracking and reminder system that identifies patients requiring follow-up imaging based on radiology reports, organizes follow-up recommendations by date and reminds patients of planned or overdue recommendations.

Historically, Philadelphia patients were only notified of further imaging recommendations through a letter sent to their home, in accordance with Philadelphia law. This meant there were unknowns: were patients actually aware of imaging recommendations and were the studies completed?

“Patient failure to comply results in delayed treatment, poor patient outcomes, additional unnecessary testing, lost revenue and legal liability,” said Dr. Jung H Yun, of the Department of Radiology, Einstein Medical Center, Jefferson Health, Philadelphia.

With this in mind, the American College of Radiology (ACR) launched the “Closing the recommendations follow-up loop” initiative, through systematic tracking and care coordination.

Yun’s group teamed up with Within Health to implement an NLP algorithm that automatically retrieved radiology reports that included both the recommended radiology exam and the recommended due date. The algorithm retrieved the patient numbers from the electronic patient file and sent text messages. The software also included an automated tracking and reminder system that checked whether patients had planned and completed follow-ups. Patients met recommendations if studies were scheduled and completed within a period of 30 days before and 60 days after the recommended due date, a compliance range defined by the American College of Radiology.

Prospective analysis was performed on all outpatient diagnostic radiology reports, excluding mammograms, generated at the facility from July 1, 2021 through April 30, 2022. Inclusion criteria for outpatient radiology reports included imaging modality, body part, and follow-up due date. Patients who opted out of SMS, or who had follow-ups scheduled but did not complete them, or whose follow-ups were not clinically indicated, were excluded.

Must Read
AI-Powered Sales Coaching: Hands-Off Virtual Training

Patients were divided into two groups, control and intervention. In the control group, there were no SMS reminder notifications until the compliance due date passed. In the intervention group, the algorithm sent an initial text reminder three weeks after the original exam with the recommended due date for follow-up exam, and then bi-weekly reminders two weeks, four weeks, and six weeks after the recommended date, unless the exam had already been scheduled or completed , until the period of ACR compliance expired. A final notification was sent on the compliance due date.

The researchers then measured adherence in both groups and compared the two. Statistical significance was set at p = 0.05.

There were a total of 275 radiology reports, 116 in the control arm and 159 in the intervention group. In the control group, 63 (54%) patients complied with follow-up, while 53 (46%) did not.

In the intervention group, 111 (70%) patients complied with follow-up while 48 (30%) did not. The treatment adherence of the intervention group was 70% versus 54% higher than the control group. The compliance rate comparison was statistically significant at p = 0.08.

The study had several limitations, including a small sample size at a single institution, no verification of active or inactive phones, and no further reminders if appointments were scheduled.

“As we continue to work with this AI software in the future, there are some considerations… we need to communicate with patients a little earlier and send them reminders even before the start of the ACR compliance range. We also want to send more reminders even if the exams are scheduled until they are actually completed, and include other means of communication such as email and integration with the patient portal. Finally, we want to involve more patients in our study, including inpatients and ER patients,” said Yun.

Must Read
AI models improve the accuracy of diagnosing coronary artery disease

Copyright © 2022 AuntMinnie.com



Please enter your comment!
Please enter your name here

Most Popular

Recent Comments