Assessment of response to medication in individuals with Parkinson's disease. (May 2019)

• Record Type: Journal Article
• Authors: Hssayeni, Murtadha D.; Burack, Michelle A.; Jimenez-Shahed, Joohi; Ghoraani, Behnaz
• Is Part Of: Medical engineering & physics. Volume 67(2019)
• Page Start: 33
• Page End: 43
• Publication Date: 2019-05
• Subjects: Parkinson's disease -- Wearable data analysis -- Feature extraction and classification -- Support vector machine; Biomedical engineering -- Periodicals; Biomedical Engineering -- Periodicals; Physics -- Periodicals; Génie biomédical -- Périodiques; Biomedical engineering; Electronic journals; Periodicals; 610.28
• DOI: 10.1016/j.medengphy.2019.03.002
• Languages: English
• ISSNs: 1350-4533

Abstract

Highlights: Development of an algorithm to automatically detect medication ON and OFF states using wearable sensors. Validation through experiments using data from subjects with Parkinson's disease (PD). Development of an algorithm customized to each subject rather than a "one-size-fits-all" approach. The ability of the algorithm to continuously detect and report medication states during daily routine activities. Development of novel signal features from wearable sensors data. Integration of feature selection and support vector machine classification with a fuzzy labeling approach. Achieved significant performance with an average accuracy of 90.5%, sensitivity of 94.2%, and specificity of 85.4%. Abstract: Background and Objective: Motor fluctuations between akinetic (medication OFF) and mobile phases (medication ON) states are one of the most prevalent complications of patients with Parkinson's disease (PD). There is a need for a technology-based system to provide reliable information about the duration in different medication phases that can be used by the treating physician to successfully adjust therapy. Methods: Two KinetiSense motion sensors were mounted on the most affected wrist and ankle of 19 PD subjects (age: 42–77, 14 males) and collected movement signals as the participants performed seven daily living activities in their medication OFF and ON phases. A feature selection and a classification algorithm based on support vector machine with fuzzy labeling was developed to detect medication ON/OFF states using gyroscope signals. The algorithm was trained using approximately 15% of the data from four activities and tested on the remaining data. Results: The algorithm was able to detect medication ON and OFF states with 90.5% accuracy, 94.2% sensitivity, and 85.4% specificity. It performed equally well for all the activities with an average accuracy of 91.3% for the activities that were used in the training phase and 88.4% for the new activities. Conclusions: The developed sensor-based algorithm could provide objective and accurate assessment of medication states that can lead to successful adjustment of the therapy resulting in considerably improved care delivery and quality of life of PD patients.