Our research is focused on the development of novel biomedical informatics technology. We seek to develop new pattern recognition methods that can combine data from different biological levels to serve as bases for individualized predictive models for diagnosis and therapy response. To achieve this…
more goal, we investigate how different system architectures influence the way biomedical data can be analyzed and interpreted, and experiment with novel approaches for data analysis. We have developed new analytical approaches for knowledge discovery when sample sizes are small, and algorithms for statistical and machine learning. We have annotated large repositories of biological data and have built systems that allow biomedical researchers to interrogate genes of interest across several studies. One area of current investigation is the calibration and discrimination of risk adjustment models in different populations, and we have proposed new methods for their assessment. Risk adjustment tools are utilized in a variety of biomedical domains, and are particularly important in monitoring safety of medical procedures, devices, and medications. We have recently collaborated with colleagues at Brigham and Women’s Hospital to develop risk adjustment models for assistive reproductive technology and percutaneous coronary interventions. We are currently working on extending a large clinical data warehouse for research at UCSD to integrate data from the electronic medical record, personal genome, and other molecular-based information for large-scale modeling.
less