PFAS predictive modeling using case control study data
Principal Investigator
Name
David Madigan
Degrees
Ph.D.
Institution
Northeastern University
Position Title
Professor
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1756
Initial CDAS Request Approval
Jan 6, 2025
Title
PFAS predictive modeling using case control study data
Summary
My project seeks to build and evaluate personalized Bayesian predictive models for various cancers from case control study data. I will build on published methodology papers such as:
Reps, J. M., Ryan, P. B., Rijnbeek, P. R., & Schuemie, M. J. (2021). Design matters in patient-level prediction: evaluation of a cohort vs. case-control design when developing predictive models in observational healthcare datasets. Journal of Big Data, 8, 1-18.
Rentroia-Pacheco, B., Bellomo, D., Lakeman, I. M., Wakkee, M., Hollestein, L. M., & van Klaveren, D. (2024). Weighted metrics are required when evaluating the performance of prediction models in nested case–control studies. BMC Medical Research Methodology, 24(1), 115.
The specific application concerns prediction of renal cell carcinoma, as a function of serum PFAS levels and other predictors. This will build on:
Shearer, J. J., Callahan, C. L., Calafat, A. M., Huang, W. Y., Jones, R. R., Sabbisetti, V. S., … & Hofmann, J. N. (2021). Serum concentrations of per-and polyfluoroalkyl substances and risk of renal cell carcinoma. JNCI: Journal of the National Cancer Institute, 113(5), 580-587.
Aims
1. Develop Bayesian predictive model methodology using data from case control studies
2. Develop and evaluate a predictive model for renal cell carcinoma using data from the PLCO, specifically Shearer et al. (2021)
Collaborators
None