Deep Learning Opens New Possibilities in Parkinson's Treatment
Posted on March 26, 2021
For Dr. Mohamed Shaban, an assistant professor of electrical engineering at the University of South Ā鶹¹ū¶³“«Ć½, deep learning computer analysis offers a powerful tool in using electroencephalography for the early detection of Parkinsonās disease.
Itās a new way of looking at an old test.
Shabanās research focuses on brain waves ā the familiar squiggly lines of an EEG ā which have been used to study neural activity for more than half a century. The latest computer-aided research techniques help reveal clues such as āsynchrony,ā an excessive synchronization of waves that indicates the cognitive impairment of a brain disorder.
āDeep learning and machine learning extract features that really canāt be detected with the eye,ā he said. āThey can be simple, they can be complicated, they can be combinations of many features, which you reach through different layers of analysis. Artificial Intelligence will do that for you.ā
In May, Shaban will present a paper at the 10th International EMBS Conference on Neural Engineering. Using an artificial neural network, he was able to classify subjects in Parkinsonās disease categories with an accuracy rate of 98 percent.
āNobody has reached that before,ā he said. āThe EEG has not been a well-known modality, but now weāre seeing something.ā
Parkinsonās disease is the second most common neurodegenerative disorder in the United States, after Alzheimerās. Symptoms include hand tremors, slowness of movement and changes in speech and handwriting, along with depression, anxiety, sleep and emotional problems. Nearly 1 million Americans live with these disorders, according to the Parkinsonās Foundation, and 60,000 Americans are diagnosed with the disease every year. The cause of Parkinsonās disease remains unknown, but both inherited and environmental factors are believed to play a role. There is no cure, though symptoms may be treatable.
Cognitive decline is an early feature of Parkinsonās, with studies suggesting that most patients exhibit sub-clinical impairment at the time of diagnosis. Cognitive function continues to decline with disease progression, resulting in dementia for more than 80 percent of patients.
āItās very important to have an early clinical diagnosis,ā Shaban said. āYou can start therapeutic treatments that slow down the neurodegenerative process.ā
EEG scans are inexpensive and noninvasive tests that use a sensor array placed on the scalp of a patient. Electrodes measure the electrical activity of the brain over time. Beta and gamma waves are related to memory and cognition.
These tests have not been used much in the diagnosis of Parkinsonās. Shaban hopes to change that.
Getting Started
Mahalia Polk, a graduate student in electrical engineering, joined Shaban on the deep learning project in the fall of 2020. Neither of them had worked with EEG test results.
āGetting started, it felt overwhelming to look at these huge datasets,ā she said. āIt was interesting and frustrating to take that first step.ā
She worked with a mathematical programming site called MATLAB to create a time-series representation of data from the wave information of EEG scans. In her office cubicle in Shelby Hall, she still has a yellow Post-it Note with tips for the āBest Patternsā to perform a function called CGB ā conjugate gradient backpropogation.
Polk has been interested in engineering since she was a teenager being home-schooled in Mobile. Her grandfather was a pipefitter who helped build power plants. Her father is a travel nurse.
Her goal is to combine engineering with medical research, and thatās exactly what sheās doing with Shaban.
āI like the idea of being able to help people like my dad does as a nurse,ā she said. āI canāt think of more impactful career than one that involves catching diseases early so they can be treated better.ā
Artificial Intelligence at South
Shaban is a native of Egypt, where his mother is a biologist and his father is a mechanical engineer. Ten years ago, they supported his decision to earn a Ph.D. in the United States.
After six months, he had second thoughts.
āI was very homesick,ā Shaban said. āI was the first generation to come to a new country with a new language.ā
Things got better. He and his wife became more comfortable. In 2019, he joined the faculty at the University of South Ā鶹¹ū¶³“«Ć½.
Shaban had used deep learning to study diabetic retinopathy, a complication of the blood sugar disorder. He brought some of the same computer-aided techniques to the study of EEG scans and Parkinsonās Disease.
He has been awarded more than $30,000 in grants from the Southeastern Center for Electrical Engineering Education.
Shaban is working with another South graduate student in genomics, using DNA sequences and mapping for the diagnosis of Parkinsonās Disease. Deep learning is part of that research, too.
āIām working now in two directions, and AI is helpful in both of them,ā he said. āArtificial intelligence can help with the early diagnosis of Parkinsonās, and it can also be helpful in genomics. We are just getting started in that area, but itās very exciting. That might be a future project.ā
Archive Search
Latest University News
-
Class Act
A South education graduate draws on her theater experience to engage t...
October 16, 2024 -
South Lands Major Grant to Study Equity in STEM Education
Dr. Kathy Thompson secures a $2.7 million NSF grant to promote access ...
October 14, 2024 -
Supply Chain Resilience
Watch for price increases, but free markets can handle a dock workers...
October 2, 2024 -
Drafting Her Start
A civil engineering graduate crosses Mobile Bay to begin her career at...
September 30, 2024