Vanderbilt leverages predictive analytics to manage OR activity

The ability to predict future case volume in operating rooms is critical to ensuring that a hospital’s staffing levels are properly matched to the projected workload to achieve maximum efficiency.


The ability to predict future case volume in operating rooms is critical to ensuring that a hospital’s staffing levels are properly matched to the projected workload to achieve maximum efficiency.

As part of its OR planning process, Vanderbilt Health is leveraging predictive analytics that run on its scheduling system so the healthcare organization can tailor its resources to accommodate forecasted changes in case volume.

“As early as 14 days out, if we happen to see a prediction that’s way below expectations, we might start selectively closing down operating rooms—and, by seven days out, we can anticipate what our final staffing levels will be,” says David Wyatt, vice president of perioperative enterprise at Vanderbilt University Medical Center.

Also See: Why improving OR efficiency must address 3 issues with technology

“It’s a bit like having a time machine,” adds Warren Sandberg, MD, professor and chair of the Department of Anesthesiology, who also holds faculty appointments in biomedical informatics and surgery. “Last year, January, February and March were light OR months. This year, we could tell at the beginning of each month that we would actually finish the month ahead of budget, and indeed we have, each time.”

By predicting how busy a given OR day in the future will be, VUMC can make advance staffing adjustments; in addition, its pharmaceutical services are able to utilize the predictions to better allocate compounded medications used by some surgical patients.

Vikram Tiwari, associate professor of anesthesiology and director of surgical business analytics, developed the models more than five years ago when he was a faculty recruitment candidate. Today, data generated by Tiwari’s models for adult and pediatric weekday OR case counts are automatically disseminated to managers and are entered into the electronic health records system.

“To our knowledge, no other medical center had mathematized their case volume predictions to any degree,” says Tiwari, who also holds faculty appointments in biomedical informatics and the Owen Graduate School of Management. “I continue to receive queries from centers around the country that want to emulate our method.”

More for you

Loading data for hdm_tax_topic #better-outcomes...