DePaul and Rosalind Franklin fund research projects that combine artificial intelligence with biomedical discovery and healthcare

DePaul University and Rosalind Franklin University of Science and Medicine are funding three faculty research projects that combine artificial intelligence with biomedical discovery and healthcare. Competitive grants initiate research among interdisciplinary teams, which include biologists, computer scientists, geographers, and physicists.

The first project will combine wearable, automated sensors with GPS mapping to predict and prevent falls and injuries among patients and military personnel. Another will analyze neurons in the brainstem to discover the boundaries that control speech and swallowing. The third project uses machine learning and video tracking to advance early detection of diseases such as Parkinson’s.

We are thrilled with the scope and visibility of these collaborative research projects from DePaul and Rosalind Franklin faculty. Together, we have the potential to see AI catalyze significant advances in human health in our lifetimes.”

Salma Ghanem, Dean of DePaul University

“This AI initiative and outstanding first-round funded pilot projects represent the next step in the ongoing research collaboration between our universities, which has so far yielded substantial results,” said Ronald Kaplan, executive vice president for research at Rosalind Franklin University. “We believe this cutting-edge work has great potential to improve health within our community.”

Wearable sensors, GPS combine to prevent injury

“We can tell a lot about a person’s health by the way they walk,” said Sungsun (Julie) Hwang, a professor of geography at DePaul. She collaborates with robotics expert Mohamed Omar Hudhaifa and data scientist Elias Uston. Their research will combine wearable technology with GPS to track a person’s gait.

In his robotics and artificial intelligence lab, Hudhaifa deploys inertial measurement units (IMUs) to track whether a person is walking, sitting, or even falling. These sensors, which measure body motion by detecting gravity’s direction and rotational speeds, can be worn as part of an exoskeleton. “Predicting harmful gait patterns and preventing falls has implications for people in health care institutions and military personnel deployed in the field,” Hudhaifa explained.

The faculty at DePaul will work with Chris Conapoy, director of the Rosalind Franklin Foreign Emergency Research Center, to use data from his lab. Ustun will use machine learning to combine GPS and IMU data, potentially predicting where injuries and falls will occur.

“Our movements create patterns, and we want to identify distinct patterns using machine learning to help assess an individual’s current health, especially those at risk,” said Uston.

The discovery of machine learning in the brainstem

The brainstem is responsible for breathing and swallowing, which may have implications for speech disorders, apnea, and sudden infant death syndrome. “Within the brainstem, neurons are not clearly differentiated,” said Jacob Furst, a professor of computing at DePaul. “Our project will look for genetic signatures that might distinguish cells when there is no apparent physical difference.”

“There is so much data being generated in the life sciences that it can be difficult to look for patterns to discover key biological insights,” said Thiru Ramaraj, associate professor of bioinformatics at DePaul. Drawing on an atlas of existing high-resolution genome-wide expression data from the adult mouse brain, Ramaraj and his team will use advanced machine learning to identify clusters and boundaries within brainstem neurons.

By working with brainstem researcher Rosalind Franklin’s brainstem researcher Kaiwen Kam’s important questions, the team hopes to develop a neuroanatomical examination, which may also have applications for other types of tissue.

“Applying computational techniques to problems that have a real impact on health is challenging and exciting,” said Ramaraj.

Diagnosing neurological disorders through AI movement patterns

Eric Landahl is a DePaul physicist who has spent most of his career making films about particles, including working at Argonne National Laboratory. “Hollywood movies are usually shot at 24 frames per second, but the atoms move at close to a billion frames per second,” Landal said. His research uses x-rays and lasers and creates huge amounts of data.

He joins Rosalind Franklin’s EunJung Hwang to use a similar approach to track the movements of mice with Parkinson’s disease. Using cloud computing and machine learning, they aim to develop a model that can predict neurological disorders before they are visible to a trained medical professional.

“This is an opportunity to be at the forefront of modern methods of data analysis,” said Landal. “This research grant gives us an opportunity to briefly step away from our day job to work on something exciting that could become something bigger in the future.”

Leave a Reply

Your email address will not be published. Required fields are marked *