Database Analysis, Data Mining, and Machine-Learning Tools

Abstract: 

Database Analysis, Data Mining, and Machine-Learning Tools

These researchers are using MSI for three projects that require distributed computation.

Anticlotting simulations to predict optimal treatment for sub-populations: The researchers use a novel computational approach that uses individual patient data and outcome evidence from two large electronic medical record (EMR) databases to conduct side-by-side clinical simulations comparing outcomes for two or more anticlotting drug and dose protocols. This is a joint project with Harvard Medical School. The researchers are beginning with development of the simulation approach.

Data mining of beneficial drug-drug interactions to enhance patient care: Working with Harvard Medical School and Allscripts, the researchers will perform a larger epidemiological study to confirm the beneficial effects of beta-blockers for breast cancer treatment. They also plan to identify what types of patients especially benefit from this treatment.

Metabolites profiling and the risk of developing osteoporosis: Working with Hebrew SeniorLife (affiliated with Harvard Medical School), the researchers will design machine-learning approaches coupled with a heuristic search and use this approach to identify biomarkers (consisting of gene expression, proteomic, and metabolomics data) to produce preliminary results for an upcoming grant proposal. 

Group name: 
chic