Researchers at the Rutgers Cancer Institute have successfully reduced patient wait times for complex cancer care by utilizing “digital twin” simulations to re-engineer clinic workflows. According to a study published in the Annals of Operations Research, this data-driven approach allowed the clinic to increase daily infusion capacity from 50 to 80 patients while slashing blood work turnaround times from 90 minutes to under 30.
How Digital Twin Technology Optimizes Clinic Flow
A digital twin is a high-fidelity, three-dimensional computer model that replicates real-world clinic operations. By inputting years of timestamped electronic health records, researchers from the Rutgers Business School and the Cancer Institute created a virtual environment to test operational changes without disrupting actual patient care. Xin Ding, a professor in the Department of Supply Chain Management, noted that the model allows administrators to identify specific patterns of patient arrival and departure, creating a statistically validated roadmap for efficiency.
The simulation revealed that adding more nursing staff—a common instinct for hospital administrators—had almost no impact on wait times. The primary bottlenecks were identified as off-site laboratory transit and a single, unorganized queue for all patient types.
Why Standard Hiring Fails to Solve Wait Times
The Rutgers study challenges the traditional hospital response of simply hiring more staff to handle patient volume. Simulations demonstrated that adding nurses shaved less than one minute off the average visit time in some scenarios. Instead, the research suggests that restructuring existing resources—such as bringing blood laboratories on-site and creating “fast track” lanes for routine care—provides a more significant reduction in wait times. According to Dr. Andrew Evens, deputy director for clinical services at the Rutgers Cancer Institute, this framework applies to any medical environment where patients move through a sequence of constrained resources, including emergency departments and surgical units.
Can Every Hospital Use This Model?
While the Rutgers approach is replicable, Dr. Evens cautions that it is not a “plug-and-play” solution. Every medical center features unique layouts, staffing levels, and patient demographics that influence workflow. Hospitals looking to adopt this method must conduct their own site-specific analysis rather than borrowing the exact configuration from the Morris Cancer Center. The need for custom modeling is highlighted by the fact that even after moving into their state-of-the-art facility, the clinic encountered new workflow puzzles, requiring further simulation-based intervention.
For maximum accuracy, digital models must be validated against months of “blind” patient data—real-world information the model has not yet processed—to ensure the simulation accurately reflects reality.
Frequently Asked Questions
What is a digital twin in a healthcare setting?
It is a computer-simulated model of a physical clinic that uses real-time patient data to predict how changes in scheduling, staffing, or resource location will impact wait times and throughput.
What was the most significant bottleneck identified?
The study found that off-site blood testing was the primary delay. By moving the laboratory on-site, the clinic reduced wait times by 75 to 90 minutes.
Does this approach only apply to cancer centers?
No. According to the research, the framework is applicable to any facility with a sequential patient flow, including emergency departments and outpatient surgical units.
Are you interested in how data science is changing the patient experience? Subscribe to our newsletter for the latest updates on medical innovation and operational research, or explore our archive for more deep dives into healthcare technology.
