When Jason Martin gives a talk about his research, he begins with the story of Mariana Bridi da Costa. The Brazilian supermodel died from severe sepsis after amputation of her hands and feet failed to stop its spread.
Martin, a fellow in allergy, pulmonary and critical care medicine, is part of a Vanderbilt interdisciplinary team that offers a high-tech approach to combating this deadly illness, one of the top 10 causes of death in the United States.
The team, which includes clinicians and informatics experts from Vanderbilt University Medical Center and computer scientists from Vanderbilt’s Institute for Software Integrated Systems (ISIS) in the School of Engineering, has developed what it believes is the first real-time system for sepsis detection.
“This is an effort to use the power of informatics to help us move from reactive to proactive medical treatment by creating tools to support the use of evidence-based clinical guidelines,” says Peter Miller, director of the Vanderbilt HealthTech Laboratory.
Miller decided to focus on sepsis because it is common, deadly, expensive and treatable. Sepsis is triggered when bacteria invade the body from outside through wounds or IV lines. The bacterial infection overstimulates the body’s immune system, setting off a cascade of inflammatory and abnormal clotting responses that can lead to organ failure and death.
When Miller and ISIS Director Janos Sztipanovits compared notes, they realized that computer-modeling tools developed by ISIS offered a chance for collaboration. But the $360,000-plus sepsis project required creating a common vocabulary and knowledge base among the team members. ISIS researchers spent two weeks at the hospital to familiarize themselves with the clinical environment.
The first part of the project involved the development of an automated early detection system that can alert doctors that a patient may be developing sepsis. The doctors came up with a formula involving patient temperature, heart rate, respiration rate and white blood count.
Currently the alerts appear on “patient dashboards” displayed on ICU workstations. In the future developers hope to add the capability of displaying the alert on doctors’ cell phones.
“Even a few years ago, we couldn’t have done a project like this because it makes decisions based on information stored on different systems that could not communicate effectively in real time,” says Ed Shultz, director of information technology integration. Patient temperature and respiratory data are handled by one system, for instance, while another handles laboratory test results. So a major technical challenge was building pipelines between the different systems and getting them to “play nicely” with each other.
Creating the decision-management system presented a different kind of problem. “It’s not easy to convert medical protocols into ones and zeros because a lot of nuance and judgment is involved,” says Martin. The ISIS team proposed breaking down guidelines into a series of independent processes that can take place sequentially or simultaneously.
“This really captures the way doctors work,” Martin says. “If we see low blood pressure, then we think of one set of treatments. If we see low blood sugar, then we think of another set. If we see the two together, then we consider a third set of possible measures we can take.”
Graduate student Janos Mathe and colleagues developed a special modeling language specifically for clinical decision-making. “Although the language is specific to sepsis management, we made the underlying technical infrastructure so general that it can model virtually any medical protocol,” Mathe says. The team already has begun applying it to a second problem, treatment of chronic heart failure.
“A key message of this project is that collaboration is very important in addressing these kinds of problems,” says Miller. “When people from different disciplines come together, they produce positive outcomes.”