Researchers at Worcester Polytechnic Institute (WPI) in Worcester, Massachusetts, recently secured $2.8 million in funding to develop a smartphone application that can detect signs of various medical conditions, such as traumatic brain injuries (TBI) and infectious diseases, in soldiers.
According to the research university, the funding support came from the Defense Advanced Research Projects Agency’s Warfighter Analytics using Smartphones for Health (WASH) program. The program’s goal is to create phone apps that can passively asses a soldier’s health, detect serious illnesses at early stages and suggest treatment options.
The funding will support WPI computer scientists’ effort to develop “machine learning algorithms that will sort through a host of data collected by sensors in smartphones to detect telltale signs of medical conditions that can affect a soldier’s readiness.”
“Often, soldiers may exhibit signs of brain injury or other illnesses, like infectious diseases, that could be sensed well before the full-blown symptoms impair their readiness,” WPI computer science professor and principal investigator for the project Emmanuel Agu said in a statement.
“Our team will research and develop machine learning algorithms that tap into smartphone sensors to passively collect data about certain behaviors that we know are related to such health issues. This will enable continuous, real-time assessment of TBI and infectious diseases afflicting soldiers, who can then be contacted by a clinician to confirm their status.”
Before developing the app, WPI scientists will first test their approach by collecting data from 100 volunteers, then 100,000 patients, before using those results to develop the machine- and deep-learning algorithms to compare patient biomarkers that correlate to symptoms of TBI and infectious diseases.
“By processing data captured by numerous sensors on the smartphones of 100,000 patients, using open-source machine learning infrastructures and cloud computing power, we will gain the critical capability to infer the health status of individual smartphone users in near real-time and with great precision,” WPI Data Science Program Director Elke Rundensteiner said. “The technology we are creating through WASH, which will discover predictive patterns in massive data sets in real time, is bound to be transformative.”