Our faculty and students explore how artificial intelligence and machine learning can transform health care. We analyze large-scale databases in search of better ways to diagnose and treat conditions including cancer, diabetes and cardiovascular disease.
As a Ph.D. student, you will help design and evaluate new algorithms and advanced learning models. You will also learn the benefits of collaboration in an interdisciplinary environment.
Our projects include:
- Machine learning and deep learning to examine the distribution and interactions of cancer cells within the tumor microenvironment while integrating multiplex tissue imaging techniques. (Chang Lab)
- Applying machine learning and deep learning techniques to better integrate imaging and omics data. (Chang Lab)
- Developing new mathematical models of metabolism and other physiologic processes and integrating these models into drug delivery platforms in the area of diabetes. (Artificial Intelligence for Medical Systems/AIMS Lab)
- Development and evaluation of machine learning models to predict glucose and prevent exercise-induced hypoglycemia and nocturnal hypoglycemia in type 1 diabetes. (AIMS Lab)
- Developing new bioinformatics tools for data analysis to identify biological mechanisms in conditions like cancer. (Xia Lab)
- Using “decision under uncertainty” theory to improve algorithms for use in medical decision support, diagnostics and other interventions, specifically in the field of diabetes. (AIMS Lab)
- Creating systems that allow the integration of data from large cancer cohorts for synthetic lethality target detection, significant noncoding mutation detection and pathway level mutational effect analysis. (Ellrott Lab)
- Developing machine-learning tools to analyze single-cell data to identify distinct cell subpopulations associated with biological and clinical phenotypes. (Xia Lab)