QUANTIFICATION OF BRADYKINESIA IN PARKINSON'S DISEASE BY USING FACIAL IMAGES AND EMG RECORDINGS

Date

2023-4

Author

Olcek, Sabri Can

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

115
views

127
downloads

Cite This

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by both motor and non-motor symptoms. The five-scale scoring system called Unified Parkinson’s Disease Rating Scale (UPDRS) is the most common tool used in symptom assessment. UPDRS III is the subsection targeting the motor symptoms and is based on the observations of the clinicians. Since the clinical assessment method is based on the visual observation and a five scale scoring, it is highly likely that the scores of two physicians differ. In fact, during multiple studies, it is observed that the scores can be biased to the dominant symptom. Furthermore, this system requires the physicians to conduct the measurements themselves, which is quite time consuming. Thus, it is important to have a repeatable, quantifiable method not just to evaluate the patient’s condition but to even detect the subtle changes. Beside Tremor, Bradykinesia is one of the main features of Parkinson’s Disease which is especially used to determine stage of the disease. The bradykinesia with rigidity can seriously hinder the patient’s movements as a result, the quality of their life. The assessment methods are mostly based on the rapid movements such as counting the number of touches made between thumb and index finger. There are many studies focusing on these tasks to measure bradykinesia by using various devices such as accelerometers, gyroscopes, and custom-built wearables. However, there is a lack of simple devices and methods that can be repeated even at home by the patient himself. In this study, we developed measurements based on a non-contact device called leap motion, using hand movements. In addition, a special hardware and software interface is developed to collect and process multi modal data by using facial images and EMG recordings. We also improved the data processing techniques to predict bradykinesia from facial movements in a better way.

Subject Keywords

parkinson’s disease, bradykinesia, updrs, emg, facial images

URI

https://hdl.handle.net/11511/103195

Collections

Graduate School of Informatics, Thesis