Thesis
Joint models of longitudinal and time-to-event data for prediction of life expectancy using age related biomarkers
Master of Science (M.S.), Drexel University
Dec 2015
DOI:
https://doi.org/10.17918/00008076
Abstract
The identification of biomarkers that can help in making an estimation of the expected lifespan of an individual is an active area in aging research. Mathematical modelling based on longitudinal experimental data is a very helpful tool in this respect. One of the promising directions in discovering and mathematical description of such relationships is the statistical joint modeling of longitudinal aging biomarker variables and time to events. This work reviews joint models for longitudinal data and survival data available in statistical literature for clinical trials that may be useful in relating biomarkers profiles and aging. In contrast to previous publications, specifically for mouse datasets concentrating on the linear trend of these biomarkers over age, this work implemented a more advanced longitudinal analysis based on a repeated measures ANOVA model with age as a discrete factor. The second novelty for the longitudinal biomarker analysis of the mouse dataset is in considering an individual animal as a subject instead of a strain as a subject, which increases the statistical power of the analysis and make consequent conclusions more convincing. The final survival analysis connecting the immune biomarkers with lifespan of mice has detected the most influential biomarker-age interaction factors for survival of the mice that may be useful in human aging research.
Metrics
17 File views/ downloads
32 Record Views
Details
- Title
- Joint models of longitudinal and time-to-event data for prediction of life expectancy using age related biomarkers
- Creators
- Natalie Khutoryansky
- Contributors
- Andres Kriete (Advisor) - Drexel University, Drexel University (1970-)
- Awarding Institution
- Drexel University
- Degree Awarded
- Master of Science (M.S.)
- Publisher
- Drexel University; Philadelphia, Pennsylvania
- Number of pages
- xv, 84 pages
- Resource Type
- Thesis
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems (1997-2026); Drexel University
- Other Identifier
- 991021888739404721