Integrating digitizing pen technology and machine learning with the Clock Drawing Test

• Main Author: Felch, Kristen (Kristen M.)
• Other Authors: Randall Davis.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2011
• Subjects: Electrical Engineering and Computer Science.
• Online Access: http://hdl.handle.net/1721.1/61285

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010. === "February 2010." Cataloged from PDF version of thesis. === Includes bibliographical references (p. 43). === The Clock Drawing Test (CDT) is a medical test for neurodegenerative diseases that has been proven to have high diagnostic value due to its ease of administration and accurate results. In order to standardize the administration process and utilize the most current machine learning tools for analysis of CDT results, the digitizing pen has been used to computerize this diagnostic test. In order to successfully integrate digitizing pen technology with the CDT, a digit recognition algorithm was developed to reduce the need for manual classification of the data collected and maintain the ease of administration of the test. In addition, the Multitool Data Analysis Package was developed to aid in the exploratory data analysis stage of the CDT. This package combines several existing machine learning tools with two new algorithm implementations to provide an easy-to-use platform for discovering trends it CDT data. === by Kristen Felch. === M.Eng.