The Department of Energy (DOE) https://www.energy.gov, announced a $1 million one year collaborative research project to develop Artificial Intelligence (AI) and Machine Learning (ML) algorithms for biomedical, personal healthcare, or for other privacy-sensitive datasets.
This funding is in response to Congressional direction for DOE to expand their successful collaborative research efforts with NIH in the areas of data and computation so the two agencies can work more closely on common scientific challenges.
The project is being led by Argonne National Laboratory https://www.anl.gov, in collaboration with Lawrence Livermore National Laboratory, University of Chicago, the Broad Institute, and Massachusetts General Hospital.
The project is titled Privacy Preserving Analysis and Learning in Secure and Distributed Enclaves and Exascale Systems (PALISADE-X). The project’s goal is to pursue innovative research to explore the development and use of privacy-preserving AI and ML for key challenge datasets such as those that are the focus of NIH’s Bridge to Artificial Intelligence (Bridge2AI program.)
The biomedical research community generates a wealth of data, but most of the data is not suitable for ML. By bringing technological and biomedical experts together with social scientists and humanists, the Bridge2AI program will help bring a solutions to this problem.
According to Barbara Helland, DOE Associate Director of Science for Advanced Scientific Computing Research (ASCR). “Coupling privacy-preserving AI methods and algorithms and DOE’s high performance computers with NIH data will accelerate biomedical research.
A potential demonstration of AI capabilities includes predicting the severity of COVID-19 using radiological datasets from multiple organizations.”