RSNA 2021 Digital X-Ray Preview

Can an AI model improve radiologist scheduling?

By Will Morton, staff writer

Wednesday, December 1 | 9:30 a.m.-10:30 a.m. | SSIN06-5 | Room TBA
In this session, researchers from Cincinnati Children's Hospital Medical Center will discuss progress on a machine-learning algorithm to optimize radiologist scheduling for radiographs. Schedules are usually constructed so that a predetermined, fixed number of radiologists cover a service. But what if the daily study volume goes up or the potential radiologist capacity drops?

As a means toward optimizing scheduling, researchers developed a model to predict study turnaround times (TAT = final report completion time) based on the scheduled complement of radiologists working in a large pediatric radiology fellowship program.

They included 397,806 radiographs in the data analysis. The team noted the model predicted an increase in the rolling seven-day mean TAT from June to September each year, which they suggest may have been due to the onboarding of new fellows. Ultimately, the model helped predict study volume with a high level of accuracy, yet prediction forecasts for shift turnaround times require further development, the team found.

Take in this session on Wednesday morning to learn more.

Last Updated np 11/15/2021 4:06:34 PM