Li, Jinhong
(2020)
Analyses of Repeatedly Measured Blood Pressure
Data from A Cohort Study with Splines.
Master's Thesis, University of Pittsburgh.
(Unpublished)
Abstract
Cardiovascular disease (CVD) is a group of disease that involve the cardiovascular system. According to World Health Organization, it is the leading cause of death worldwide and hypertension is a major risk factor of CVD. Pregnancy is a special “window” for women and the physiological change could reflect enduring risk for CVD. In a recent study, researchers were interested in whether placental malperfusion could predict risk of CVD 8-10 years after delivery, and blood pressure (BP) is one of the endpoints of interest. In this thesis, we studied whether placental malperfusion is predictive for elevated BP. BP was repeatedly measured for three times during the office visit, thus the data had a longitudinal structure. One challenge is that BP fluctuates with regards to time during a day, and it is essential to adjust for the potential confounding effect of time in regression analyses. Splines provide a powerful tool to adjust for such relationship with abundant flexibility. In this thesis, natural cubic splines (NCS) and smoothing splines (SS) were considered and compared. As a consequence, application of the splines could identify significant predictive biomarkers, with flexible adjustment of the time effect. NCS is easier to use while SS is more flexibile.
Public health importance: Limited number of research have been done about the prognostic utility of placental malperfusion on risk of hypertension and CVD. Splines provide a powerful and flexible tool to characterize such a relationship.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
30 July 2020 |
| Date Type: |
Publication |
| Defense Date: |
17 April 2020 |
| Approval Date: |
30 July 2020 |
| Submission Date: |
15 May 2020 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
43 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
School of Public Health > Biostatistics |
| Degree: |
MS - Master of Science |
| Thesis Type: |
Master's Thesis |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
natural cubic splines, smoothing splines, semiparametric mixed-effects models, blood pressure |
| Date Deposited: |
30 Jul 2020 18:46 |
| Last Modified: |
30 Jul 2020 18:46 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/39044 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}