iDASH Data, Tools, Algorithms, and Training: Current Status and Future Plans

Date: 

Mon Jun 15, 2015

Host: 

Lucila Ohno-Machado
UC San Diego
 

Category: 

Data Modeling and Integration

VIEW RECORDING
DOWNLOAD SLIDES
 

ABSTRACT

iDASH (integrating Data for Analysis, ‘anonymization,’ and Sharing) is an NIH-funded national center for biomedical computing that started in late 2010 and will complete 5 years this fall. It is focused on developing algorithms and tools to facilitate privacy-protecting data sharing, and in training the next generation of biomedical data scientists. Through collaboration with several institutions, iDASH has been addressing important challenges such as how to ethically and securely share data for research without compromising patient and institutional privacy. iDASH funded several demonstration projects addressing biosample and data sharing in culturally and ethnically diverse communities, how to quantify the risk of re-identification in disclosed data, and how to decompose multivariate models so that data can be used in analyses without leaving their home institutions. This presentation will provide an overview of how the project evolved in the past years and current resources that iDASH is making available to the biomedical research community now.

 

SPEAKER BIOGRAPHY

Dr. Ohno-Machado, associate dean for informatics at UCSD School of Medicine, directs the Health System Department of Biomedical Informatics, an informatics research, teaching, and service unit at UCSD. She directs iDASH, an NIH-funded national center for biomedical computing and bioCADDIE, a consortium to develop a biomedical and healthcare data discovery index ecosystem. Her research has been focused on privacy-protecting data sharing and construction and evaluation of data mining and decision support tools for biomedical research and clinical care. These tools are based in statistical and machine learning on large biomedical datasets. Her team develops tools to make patient data available for research without compromising patient privacy, and to integrate and analyze massive amounts of data efficiently through distributed computation. She is principal investigator for the the patient-centered Scalable National Network for Effectiveness Research (pSCANNER) project, a clinical data research network funded by PCORI, and the Informatics Core of the Clinical and Translational Research Institute at UCSD.