Model for the Future of Health:

Thomas Heldt believes in the power of patient data—the physiological measurements collected in intensive care units, operating rooms and emergency rooms—from medical devices logging hundreds of samples per second.

“What if we didn’t throw away all that data?” Heldt asks. He and his research colleagues at IMES analyze patient data in an effort to help clinicians deepen and personalize patient care, and potentially alert them to crises. “What if we could move away from a care paradigm that is reactive . . . to one that is predictive?”

Yet the first hurdle, even in the age of big data, is harnessing the information.

“The infrastructure in the hospital was never set up to keep that data…. (Plus) devices from different vendors don’t really communicate. It’s very difficult to get data on a common time axis, so you can see what happened with that particular patient.” Partnerships with medical device manufacturers are extremely helpful. And when that doesn’t work, there is always “hacking,” Heldt says.

Yet getting at the data is only the beginning. To move beyond hypotheses, Heldt’s group uses mathematical modeling and model-based data integration.

“We’re standing on about 200 years of hard, quantitative physiological research (of) various organ systems,” says Heldt. “By using that knowledge to build mathematical models of how a physiological system ought to behave and comparing it to experimental data, we might understand the system (and patient health) more deeply.”

Heldt and his colleague George Verghese have pursued such work under an NIH grant since 2002. One concrete application is intracranial pressure (ICP) monitoring. Faisal Kashif did his PhD thesis with Heldt and Verghese at MIT on the functional relationship between ICP, cerebral blood flow and arterial blood pressure (ABP) – finding a way to estimate ICP noninvasively by monitoring the other two.

“The way ICP is currently monitored is by drilling a hole into the skull and advancing a catheter in the cranial cavity. Let me show you,” says Heldt. He keeps an everyday, ten-dollar hand drill in his office to show its similarity to the surgeon’s tool. “So you only do this in patients who are very sick, where drilling a hole in your skull is the least of your problems.”

Yet Heldt believes other brain-injured and neurologically challenged patients could benefit from noninvasive ICP monitoring, and clinicians agree. The research—first validated against archived data in the UK—is now being further validated with help from colleagues at Beth Israel Deaconess Medical Center, Boston Children’s Hospital and Boston Medical Center.

“It’s always magic how that happens,” says Heldt. “We’re very fortunate in the Boston area to have so many clinicians who think deeply about the kind of care they provide and how technology could make a difference.”

Clinicians from the neonatology departments at Boston Children’s and Beth Israel Deaconess Medical Center also work with Heldt on his research into brain injury in premature infants. Heldt hopes to shed light on why some preemies develop devastating brain injuries in their first few days, while others do not.

Interested in both physics and medicine during his education in Germany, Heldt says he was taken under the wing of a teacher/surgeon who let him observe children’s heart surgeries. “For me that was incredibly formative.”

Later, studying at Harvard-MIT HST with Roger Mark, Heldt found that through collaboration, he could pursue his ambitious goals for human health. Today, he’s eager to engage not only with the medical community, but also with industry, including the mircoelectronics sector, as a collaborator with MIT’s Medical Electronic Device Realization Center (MEDRC).

“It takes a broad spectrum of people to make miniaturized, more powerful devices that have the potential to impact medical care,” says Heldt. Yet such tools have the promise of improving lives and “reducing the cost of healthcare by keeping patients out of the hospital.”

“The people who convene around these kinds of problems, we usually get along really well,” Heldt adds. “People are enthusiastic. Students are enthusiastic. We want to alleviate suffering.”