Amanda Randles won $250,000 ACM prize in computer science

To that end, Randles, a professor of biomedical sciences at Duke University’s Pratt School of Engineering, spends his time building some of these virtual simulations.

In particular, it focuses on simulating blood flow and cell movement throughout the body. His recent work earned him the Association for Computing Machinery’s $250,000 prize in computer science.

“Its innovative techniques will not only deepen our understanding of diseases, but also herald a new era of biomedical simulation,” Salil Parekh, CEO of Infosys, which is funding the prize, said in a statement.

Use data from your Apple Watch

Today’s standard fitness wearable devices can track a person’s heart rate during daily activities. However, if they could also track changes in blood flow in real time, then it could help doctors move from “reactive care to proactive care,” Randles said.

In other words, it could help doctors identify signs of life-threatening illnesses like heart disease much earlier, which could lead to better treatment. Heart disease is the leading cause of death in the United States, accounting for one in five deaths each year.

While there are privacy concerns, a virtual twin that tracks your health daily would be revolutionary for healthcare. However, one of the obstacles people like Randles face is data overload.

Since your heart beats 100,000 times a day, that’s a huge amount of data. Randles and his team are working to figure out how to take snapshots of moments and apply them to larger scenarios.

If you sit at your computer for a few hours each morning for a week, for example, the model may not need to incorporate every second.

Once you have that personalized baseline, “we need to have ways to calibrate when you’ve gone off the rails and it no longer fits,” Randles said.

The model would be able to detect whether plaque is developing in the heart, for example.

Although she hopes that typical wearable devices will provide good enough data for the model, Randles said some patients with heart disease may need medical-grade devices.

These types of portable blood cards could be on the horizon, Randles said. “It’s not decades away,” she said. “I think we’ll see it in the next five to seven years.”

Currently, the circulatory system is only one part of the entire human body, and Randles wants to integrate the brain and other systems into the virtual twin concept. This technology will be available in at least a decade, she said.

Meanwhile, Randles’ simulations are already helping doctors in other ways.

A personalized 3D map of your circulatory system

Using Randles simulations, doctors can determine when a patient needs a stent to improve blood flow to their heart in a non-invasive way. The traditional method involves inserting a guide wire into the coronary artery to measure pressure.

“With virtual models, we don’t need to put the guidewire in the patient,” Randles said.

Randles is working to allow doctors to virtually try different treatment options, like stent placement, to see which one is best for the patient before they enter the operating room.

Right now, that requires a lot of computing power, so his lab is incorporating machine learning to speed up the process.

Cancer cell tracking

When cancer cells circulate in the bloodstream, they can sometimes acclimate to another part of the body and form new tumors, called metastases.

In another part of his research, Randles examines how a cancer cell moves. In his simulations, Randles changes different parameters, such as how the size of the cell’s nucleus affects its movement.

Once they have enough data on the characteristics of different cells and how they move, doctors may be better able to predict how and where certain cancer cells metastasize.

“What makes cancer cells more likely to go to the brain or breast,” she asked. “If we can understand what drives the cell to go in this direction, it can inform treatments,” she said.