The center will serve as a test-bed infrastructure to facilitate the development of various analytical and engagement tools. Computational complexity in such analysis is driven by the facts that the data are both heterogeneous (in different formats and platforms) and high-dimensional (number of variables >> number of samples), and combine both static data (e.g., inferring differential gene expression after drug exposure) and longitudinal data (e.g., health complications of an individual obtained from electronic health records; changing of symptoms during a trial) in the time domain.
Researchers at the Center for Artificial Intelligence Driven Health Data Systems and Analytics are working to utilize the power of data analytics, machine learning, high-performance computation, and well-curated datasets to advance solutions to the most prominent world health disorders. This is accomplished through a research ecosystem that allows faculty and partners to work together on the range of issues related to the disorders. This unified, efficient, and powerful data platform that helps aggregate and harmonize datasets from variety of healthcare partners and provides extensive capabilities and resources for the teams to investigate the disorders.
Current research projects include:
- Single-cell Breast cancer therapeutics. This project will use model-based unsupervised machine learning methods to infer drug response in triple-negative breast cancer using single-cell RNASeq, and will predict drug response in triple-negative breast cancer patients using game theoretic models and RNASeq data
- Antidepressant response in Major Depressive Disorder. This project will use supervised machine learning methods to predict drug responses in depression patients treated with antidepressants using metabolomics, genomics, and clinical data.
- Predicting surgical readmissions in Diabetic Patients.