Health and Behavior
Monitoring of Parkinson’s Disease PatientsLed by Behnaz Ghoraani, Ph.D.
Behnaz Ghoraani, Ph.D., is a Faculty Fellow at the Institute for Sensing and Embedded Network Systems Engineering at Florida Atlantic University (FAU). Ghoraani completed her Ph.D. in Electrical and Computer Engineering at Ryerson University, in Toronto, Canada, in 2010, and was a postdoctoral fellow in Faculty of medicine at University of Toronto (2010-2012). Ghoraani is the founder and director of the Biomedical Signal and Image Analysis (BSIA) Lab at FAU. At the BSIA lab, our mission is to develop a research program that fosters interaction with undergraduate and graduate students. The multidisciplinary research at BSIA lab has largely focused on developing innovative signal analysis solutions to tackle big bottlenecks in data analytics with an emphasis on automated and reliable clinical decision-making systems and effective therapeutic techniques. For more information on Behnaz Ghoraani’s research group click here.
Parkinsons’ Disease (PD) is a chronic movement disorder that increases with time. It includes three observable abnormalities: tremor, bradykinesia/akinesia (impairment of the power of voluntary movements), and balance impairment.
Levodopa is prescribed as a medication to improve these motor impairments, but its side effect is dyskinesia. The dose of Levodopa needs to be progressively adjusted depending on the interval between the “ON” and “OFF” states that is different from patient to another. There is need to discriminate between the two states the “ON” state when the medications (levodopa) are working and the “OFF” state when they wore off. This REU project will involve developing a programing framework that automates the discrimination between the two stages. The REU student’s contribution will specifically consist of developing a MATLAB program that characterizes the ambulatory signals related to the gait data form patients with PD. The student will perform the necessary experiments required to evaluate the reliability of the developed program. The developed program will be ultimately applied for diagnosis, as well as therapy management of PD.
Left atrial arrhythmias, and in particular left atrial fibrillation, constitute a cardiac condition in which the electrical conduction pathway within the heart mis-fires leading to abnormal heart rhythm.
While the exact etiology of the disease is still unknown and under investigation, several methods have been adopted in the attempt to manage and treat the disease after detection. Cardiac ablation is the preferred approach, where a catheter is navigated inside the heart through the peripheral vasculature and used to deliver high radio-frequency energy to the myocardium in a localized manner to generate scar tissue that will electrically isolate the conduction pathway in the region of interest. However, in order to identify the arrhythmic site and plan the ablation procedure, it is critical to analyze the electrophysiology information from the patient’s cardiac signals. This REU project will involve developing a programing framework that automates the characterization of such cardiac signals. The REU student’s contribution will specifically consist of developing a MATLAB program that characterizes the cardiac signals related to the atrial arrhythmia project. The student will perform the necessary experiments required to evaluate the reliability of the developed program. The developed program will be ultimately applied for diagnosis, assessment, as well as planning and guidance of left atrial arrhythmias.
Mild cognitive impairment and Alzheimer’s disease are the most common causes of cognitive deterioration in older adults. Early diagnosis of cognitive decline, could establish a baseline, and track cognition over time helping to ensure appropriate care for cognitive health as those affected age.
However, less than half of elders are presently screened and diagnosed by outpatient providers for dementia. Gait, as the motor task component of motor- cognitive assessments, is often difficult to perform due to mobility impairments, risk of falling, or lack of time and space in busy clinical settings. This REU project will involve developing a programing framework to examine other motor movements in trunk and upper extremities using wearable sensors. The REU student’s contribution will specifically consist of developing a MATLAB program that applies previously developed data analysis algorithms on the collected patient data. The student will perform the necessary experiments required to evaluate the reliability of the developed program. The developed program will be ultimately used to develop a more clinically applicable motor-cognitive performance measure to identify mild cognitive impairment and Alzheimer’s disease in older adults.