I am currently working as a Biostatistician focusing on mRNA and translational research in Translational and Early Development Biostatistics at Sanofi.
I completed my PhD degree in Biostatistics at the University of Pittsburgh, advised by Dr. Jong-Hyeon Jeong. My dissertation research area is time-to-event data analysis, specifically, deep learning for survival data. During my PhD study, I had also worked as a Graduate Student Researcher at
MYHAT group at UPMC, collaborating with physicians and clinical researchers to study risk/protective factors of mild cognitive impairment and dementia.
My statistical expertise include survival analysis, machine learning and deep learning, omics data analysis, and longitudinal data analysis. I am particularly interested in novel statistical applications in artificial intelligence in medicine and drug development.
Awards
ASA Student of the Year, ASA Pittsburgh Chapter, 2022
ASA Lifetime Data Science (LiDS) Section Student Paper Award at JSM, 2021
Outstanding Master’s Student, University of Washington School of Public Health Awards of Excellence, 2017
University of Iowa Student Employee of the Year Recognition, 2014
Selected Publications
Methodology
Jeong, J. H. & Jia, Y. (2022+). Causal Deep Learning for Prediction of Individual Event Times. arXiv preprint arXiv:2203.10207. Submitted.
Jia, Y. & Jeong, J. H. (2022+). DeepCENT: Prediction of Censored Event Time via Deep Learning. arXiv preprint arXiv:2202.05155. Under Review.
Jia, Y. & Jeong, J. H. (2021). Deep Learning for Quantile Regression under Right Censoring: DeepQuantreg. Computational Statistics & Data Analysis, in press. link
Jia, Y. & Jeong, J. H. (2021). Cause-specific Quantile Regression on Inactivity Time. Statistics in Medicine, 40(7), 1811-1824. link
Collaboration
Lee, S., Jia, Y., Snitz, B. E., Chang, C. C. H. & Ganguli, M. (2022). Assessing Social Cognition in Older Adults: A Population-Based Study. Alzheimer Disease & Associated Disorders – An International Journal, 30(4), S88-S89.
Runk A., Jia, Y., Liu, A., Chang, C. C. H., Ganguli, M & Snitz, B. E. (2021). Associations between visual acuity and cognitive decline in older adulthood: A 9-year longitudinal study. Journal of the International Neuropsychological Society, 1-11.
Bhojak T., Jia, Y., Jacobson, E., Snitz, B. E., Chang, C. C. H. & Ganguli, M. (2021). Driving Habits of older adults: A Population-Based Study. The American Journal of Geriatric Psychiatry, 29(4), S128.
Jia, Y., Chang, C. C. H., Hughes, T. F., Wang, S., & Ganguli, M. (2020). Predictors of Dementia in the Oldest Old: A Novel Machine Learning Approach. Alzheimer Disease & Associated Disorders, 34(4), 325-332.
Cohen, A. D., Jia, Y., Smagula, S. F., Chang, C. C. H., Snitz, B. E., Jacobson, E., & Ganguli, M. (2020). Cognitive functions predict trajectories of sleepiness over ten year: a population-based study. The Journals of Gerontology: Series A, glaa120.
Smagula, S. F., Jia, Y., Chang, C. C. H., Cohen, A., & Ganguli, M. (2019). Trajectories of daytime sleepiness and their associations with dementia incidence. Journal of Sleep Research, 29(6): e12952.
Ganguli, M., Jia, Y., Hughes, T. F., Snitz, B. E., Chang, C. C. H., Berman, S. B., ... & Kamboh, M. I. (2019). Mild Cognitive Impairment that Does Not Progress to Dementia: A Population‐Based Study. Journal of the American Geriatrics Society, 67(2), 232-238.
Selected Presentations
JSM, August 2021 (virtual oral presentation)
ENAR, March 2021 (virtual poster presentation)
ICSA Applied Statistic Symposium, December 2020 (virtual poster presentation)
ENAR, March 2020 (virtual oral presentation)
Selected Statistical Packages
DeepQuantreg: A Python package (with GPU acceleration) for deep (Deep) censored quantile (Quant) regression (reg). link
QRegIT: An R package (with functions written in Rcpp) for quantile (Q) regression (Reg) on inactivity (I) time (T). link
Yichen Jia
yij22@pitt.edu
PhD in Biostatistics
University of Pittsburgh
Fall 2017 - Spring 2022