The Center for Predictive Computational Phenotyping is focused on significantly advancing the state of the art in computational methods for transforming large, heterogeneous, high-dimensional data sources into predictive models for biomedicine. Specifically, we are focusing on a broad range of problems that can be cast as computational phenotyping. CPCP is organized into projects which are focused on model problems for computational phenotyping, labs which are developing innovative methodological approaches, and two key cores.

EHR-based Phenotyping Project

Neuroimage-based Phenotyping Project

Epigenome-based Phenotyping Project

Transcriptome-based Phenotyping Project

Phenotype Models for Breast Cancer Screening Project

Stochastic Modeling Lab

Low-dimensional Representations Lab

Data Management Lab

Value of Information Lab

Software Engineering and High-Throughput Computing Core

Bioethics Core

Recent CPCP Publications

Improving breast cancer risk prediction by using demographic risk factors, abnormality features on mammograms and genetic variants. Feld S, Woo K, Alexandridis R, Wu Y, Liu J, Peissig P, Onitilo A, Cox J, Page D, Burnside E. Proceedings of the AMIA Annual Symposium, 2018

Privacy-preserving ridge regression with only linearly-homomorphic encryption. Giacomelli I , Jha S, Joye M, Page CD, Yoon K. Proceedings of Applied Cryptography & Network Security (ACNS), 2018

Opportunities and obstacles for deep learning in biology and medicine. Ching T et al. Journal of the Royal Society Interface 15:20170387, 2018

MatchCatcher: A debugger for blocking in entity matching. Li H, Konda P, Suganthan P, Doan A, Snyder B, Park Y, Krishnan G, Deep R, Raghavendra V. Proceedings of International Conference on Extending Database Technology (EDBT), 2018

Utility of genetic testing in addition to mammography for determining risk of breast cancer depends on patient age. Feld S, Fan J, Yuan M, Wu Y, Woo K, Alexandridis R, Burnside E. Proceedings of the AMIA Informatics Summit, 2018

Using machine learning algorithms to predict risk for development of calciphylaxis in patients with chronic kidney disease. Kleiman R, LaRose E, Badger J, Page D, Caldwell M, Clay J, Peissig P. Proceedings of the AMIA Informatics Summit, 2018

Quantifying predictive capability of electronic health records for the most harmful breast cancer. Wu Y, Fan J, Peissig P, Berg R, Tafti P, Yin J, Yuan M, Page D, Cox J, Burnside E. Proceedings of SPIE Medical Imaging, 2018

Applying family analyses to electronic health records to facilitate genetic research. Huang X, Elston RC, Rosa GJ, Mayer J, Ye Z, Kitchner T, Brilliant MH, Page D, Hebbring SJ. Bioinformatics 34(4):635–642, 2018

Statistical tests and identifiability conditions for pooling and analyzing multisite datasets. Zhou HH, Singh V, Johnson SC, Wahba G, and the Alzheimer’s Disease Neuroimaging Initiative. Proceedings of the National Academy of Sciences USA, 2018

Automated and robust quantification of colocalization in dual-color fluorescence microscopy: A nonparametric statistical approach. Wang S, Arena E, Elicieri K, Yuan M. IEEE Transactions on Image Processing 27(2):622-636, 2018