Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Analyzing Actigraphy Data to Study the Efficacy of Dynamic Arm Support for Duchenne Muscular Dystrophy

Elkhadrawi, Mahmoud (2021) Analyzing Actigraphy Data to Study the Efficacy of Dynamic Arm Support for Duchenne Muscular Dystrophy. Master's Thesis, University of Pittsburgh. (Unpublished)

PDF (Elkhadrawi_etdPitt2020)
Download (1MB) | Preview


Duchenne muscular dystrophy (DMD) is the most common form of muscular dystrophy and it is the most common fatal genetic disorder diagnosed in childhood. DMD almost always affects boys as it results from a genetic mutation in the X chromosome that programs proteins critical to muscle integrity. DMD affects approximately 1 in every 3,500 to 6000 male births in the US (about 20,000 new cases each year worldwide). Typically, boys with DMD lose their ability to walk between the ages of ten and fourteen. By the late teenage years as the muscles deteriorate, significant loss of strength in the upper body results in loss of arm function and independence in everyday tasks. In this study we investigate the usage of an Actively Actuated Device called KINOVA-O540 as an assistive technology by such individuals during activities of daily living. This study compared the usage of KINOVA-O540 and no-KINOVA-O540 usage through the participation of individuals with DMD during Performance of Upper Limb (PUL) tests. PUL tests represent the activities of daily living. Specifically, three dimensional actigraphy data (accelerometer data) were used for this comparison. We have developed a feature selection and support vector machine (SVM)-based classification algorithm to identify when the KINOVA-O540 device is used based on the recorded actigraphy. Moreover, we showed how the selected features that separate the KINOVA-O540 usage from other data change as the success rate changes in PUL tasks. As the features that separate KINOVA-O540 from no-KINOVA-O540 usage are not optimized to identify task success, we then modified the feature selection and classification algorithm to separate the success from no-success in PUL tasks based on the recorded actigraphy. We showed that such an algorithm based on actigraphy is more successful in classifying between success and no-success when KINOVA-O540 device is used. This is a significant outcome as it shows that KINOVA-O540 can be used together with actigraphy to identify how successful DMD patients are during activities of daily living.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Elkhadrawi, Mahmoudmae116@pitt.edumae116
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorAkcakaya,
Committee MemberSeijdic,
Committee MemberMao,
Committee MemberBendixen,
Date: 26 January 2021
Date Type: Publication
Defense Date: 6 November 2020
Approval Date: 26 January 2021
Submission Date: 26 October 2020
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 50
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Electrical and Computer Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: Duchenne Muscular Dystrophy, machine learning, SVM, Sequential forward selection, accelerometry, dynamic arm support
Date Deposited: 26 Jan 2021 18:36
Last Modified: 26 Jan 2021 18:36


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item