Abstract
Cardiac related diseases are a serious health risk for adults. Consequently, therapies exist to treat these aliments such as heart transplant and medication. Heart transplant remains the gold standard for treating severe heart failure, however left ventricular assistive devices, a cardiac blood pump, are become a viable long term treatment. Unfortunately, with the benefits of these devices come risks of clot formation. These occlusions can cause strokes, further cardiac damage, or even death. Therefore, it is critical that these occlusions be detected as early as possible. This work presents an expanded method to non-invasively monitor the condition of a Thoratec HeartMate II ventricular assist device through the application of a boosted classification tree. In addition, both inflow and outflow blockages measured at aorta and pump locations were experimentally tested on a cardiac phantom. The proposed method presents a potential outpatient diagnostic method that may assist experienced cardiologists in their treatment of LVAD patients.
Library of Congress Subject Headings
Rotary pumps--Testing; Blood--Circulation, Artificial; Heart--Left ventricle; Signal processing--Digital techniques
Publication Date
10-2019
Document Type
Thesis
Student Type
Graduate
Degree Name
Mechanical Engineering (MS)
Department, Program, or Center
Mechanical Engineering (KGCOE)
Advisor
Jason Kolodziej
Advisor/Committee Member
Steven W. Day
Advisor/Committee Member
Mark Kempski
Recommended Citation
Reuter, Steven Paul, "LVAD Occlusion Condition Monitoring Using Boost Classification Trees" (2019). Thesis. Rochester Institute of Technology. Accessed from
https://repository.rit.edu/theses/10243
Campus
RIT – Main Campus
Plan Codes
MECE-MS