The digital symbol digit test : screening for Alzheimer's and Parkinson's
Name
1108620165-MIT.pdf
Size
808.29 KB
Format
Adobe PDF
Checksum (MD5)
1a431b7a8cc884b5d4bff09d4086b49a
Author(s)
Huang, Lauren(Lauren A.)
Advisor(s)
Randall Davis.
Date Issued
2017
Publisher
Massachusetts Institute of Technology
Abstract
Neurodegenerative diseases affect the cognition of millions of people worldwide, degrading their quality of life and placing a burden on their families. Early identication can be extremely beneficial in treating or slowing down the onset of these diseases. One technique used to identify early warning signs is the use of cognitive tests. Unfortunately, grading these tests is subjective. In this study, we quantitatively evaluated the digital Symbol Digit Test (dSDT), in which patients translate symbols into digits based on a given mapping. In collaboration with Dr. Penney of Lahey Clinic, we administered the dSDT to over 170 patients using a digitizing pen that measures its position on the page and the pressure applied. We developed support vector machine and logistic regression classifiers that indicate Alzheimer's Disease and Parkinson's Disease with an area under the curve of 0.957 and 0.963, respectively.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 81-82).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
Persistent DSpace Link
