Lockheed Martin adapts the data analytics techniques it uses to detect launched missiles to identify sepsis, a potentially fatal bloodstream infection, 14 to 16 hours earlier than current industry methods.
Aerospace and defense firm Lockheed Martin is using the signal processing and data analytics techniques it employs to analyze the streaming sensor data from launched missiles to detect sepsis, a potentially fatal whole-body inflammation caused by severe infection by at least 14 to 16 hours earlier than the existing industry methods.
“Vitals and lab data are, essentially, continuously updated streams of information – just like missile signals detected by our defense systems," explained Melanie Lang, Lockheed Martin business development lead within Information Systems & Global Solutions. "Lockheed Martin took insights from real-time, streaming sensor data, detecting missiles at mach speeds, and reapplied those same techniques to real-time patient data.”
Sepsis is not a specific disease but a severe medical condition caused by an overwhelming immune response to bacterial, viral, fungal or parasitic infections. Chemicals released into the blood to fight infection trigger widespread whole-body inflammation leading to shock, organ failure and death, if it is not detected early and addressed in time.
Sepsis is a very common and deadly disease killing 6 million infants and young children and 100,000 new mothers every year in the world. In the United States, sepsis affects 750,000 people every year and kills 258,000 of them and its treatment-related expenses account to more than $20 billion.
Because the clinical symptoms of sepsis are not-so-specific and its deterioration is rapid, it is hard to detect it in time. The existing method for detecting sepsis, Systemic Inflammatory Response Syndrome (SIRS) has high false negative rate of 31 percent (not flagging patients as having sepsis when they do) and false positive rate of 65 percent (flagging patients as having sepsis when they do not), which burdens healthcare organizations.
Now Lockheed Martin developed a predictive formula, using its advanced analytic framework called Sia, to continuously monitor and analyze patients’ vital signs, lab reports and other indicating features and detect sepsis 14 to 16 hours earlier than current methods.
In an initial trial involving 4,500 patients at the University of Pennsylvania, Lockheed Martin’s new approach correctly alerted sepsis presence 90 percent of the time while falsely diagnosing only one percent of the time. This gives it a 90% detection rate and 99% accuracy. In contrast, SIRS’ detection rate is 69% and accuracy is 35%.
If detected early, sepsis can be treated using strong antibiotics. But sepsis infections turn life-threatening in a matter of hours. In fact, for every hour of delay in treatment, the mortality rate for sepsis increases by 7 percent. This underscores the importance of an early detection system.
“Our current sepsis algorithm is targeted for the general population,” says Mike Draugelis, chief data scientist at Lockheed Martin Information Systems & Global Solutions. “But with additional research, we can focus on categories of patients: the elderly, the very young, cancer patients and heart disease patients. By focusing on similar patient groups, we should be able to improve our accuracy even further to drive an even earlier diagnosis of sepsis.”
Lockheed Martin believes that data analytics framework and predictive algorithms used in sepsis detection also have the potential to detect many other conditions, such as myocardial infarction or the onset of diabetes and blood clots, among others, with high accuracy.
“Lockheed Martin’s solution leverages the best in science, clinical protocols and data processing to achieve unparalleled levels of detection accuracy" said Heather Lavoie, President of Geneia, a Capital Blue Cross subsidiary that focuses on health care innovations. "We see broad potential to use this solution for early detection and high accuracy across numerous conditions to cost-effectively improve the health of our customers.”
Lockheed Martin’s new predictive analytics platform, with its unparalleled accuracy and early detection, facilitates timely medical intervention saving thousands of lives and billions of dollars of avoidable healthcare expenditure.