– Researchers from Florida Atlantic University’s (FAU) College of Engineering and Computer Science have developed machine learning algorithms that can continuously monitor patients and estimate total Parkinsonian tremor as patients perform various free body movements in their natural environments.
Parkinson’s disease is the second most common age-related neurodegenerative disorder after Alzheimer’s, researchers noted, affecting 7 to 10 million people worldwide. In the US, about 1 million people are thought to have Parkinson’s, and about 60,000 Americans are diagnosed each year.
Tremors are a significant marker of Parkinson’s disease. These involuntary movements can take a serious toll on patients’ quality of life, interrupting activities like eating and writing. Currently, neurologists measure tremors using the Unified Parkinson’s Disease Rating Scale (UPDRS), which requires patients to perform specific tasks.
Unfortunately, the UPDRS evaluation is based on an onsite physical exam, and the test only provides a snapshot of the patient’s daily tremor experience.
To treat and track tremors in patients with Parkinson’s more effectively, researchers from FAU, in collaboration with the Icahn School of Medicine at Mount Sinai and the University of Rochester Medical Center, have built machine learning algorithms that can continuously monitor patients in day-to-day life.
“A single, clinical examination in a doctor’s office often fails to capture a patient’s complete continuum of tremors in his or her routine daily life,” said Behnaz Ghoraani, PhD, senior author, an assistant professor in FAU’s Department of Computer and Electrical Engineering and Computer Science, and a fellow of FAU’s Institute for Sensing and Embedded Network Systems (I-SENSE) and FAU’s Brain Institute (I-BRAIN).
“Wearable sensors, combined with machine-learning algorithms, can be used at home or elsewhere to estimate a patient’s severity rating of tremors based on the way that it manifests itself in movement patterns.”
Many approaches used to track tremors today are task-dependent, and only provide moderate to good performance because of limitations in underlying algorithms to classify tremor patterns from patients’ free body movements. With machine learning, providers would be able to track and quantify resting tremor within daily living activities and separate rhythmic shaking from normal activities, without patients having to perform standardized tasks.
Researchers used two different machine learning algorithms to estimate tremor severity, resting and action, using data collected from two sensors placed on patients’ most affected wrist and ankle. The team collected data as patients performed a variety of activities, including walking, resting, eating, and getting dressed.
The results showed that one machine learning approach, the gradient tree boosting method, estimated the whole tremor as well as the resting tremor sub-score with a high level of accuracy, and in most cases, with the same results estimated using the UPDRS.
The machine learning method also showed the decline in tremors after patients took their medication, even in cases where results did not match total tremor sub-scores from the UPDRS assessments.
“It is especially interesting that the method we developed successfully detected hand and leg tremors using only one sensor on the wrist and ankle, respectively,” said Murtadha D. Hssayeni, co-author and a PhD student in FAU’s Department of Computer and Electrical Engineering and Computer Science.
The machine learning method provides the highest performing among the UPDRS task-dependent methods and all the task-independent tremor estimation methods to date.
“This finding is important because our method is able to provide a better temporal resolution to estimate tremors to provide a measure of the full spectrum of tremor changes over time,” said Ghoraani.
The study demonstrates the potential for machine learning technology to improve neurological disease treatment.
“For the millions of people around the world who are affected by Parkinson’s disease, professor Ghoraani and her collaborators offer great promise for a reliable approach to monitor their severity of tremors during the course of a typical day,” said Stella Batalama, PhD, dean of FAU’s College of Engineering and Computer Science.
“Moreover, the method our team has developed will provide clinicians with vital information to effectively manage and treat their patients with this disorder.”
Credit: Google News