Joint DMS/NLM Initiative on Generalizable Data Science Methods for Biomedical Research (DMS/NLM)
NSF 19-500       https://www.nsf.gov/pubs/2019/nsf19500/nsf19500.htm

Significant advances in technology coupled with decreasing costs associated with data collection and storage have resulted in unprecedented access to vast amounts of health- and disease-related data. Biomedical data includes genomics data from next-generation sequencing, data from different imaging modalities, real-time and static data from wearable electronics, personal mobile devices, and environmental sensors, observational health data, and clinical data from hospitals, insurance, and electronic medical records including personal health records. This program seeks to leverage advances in emerging areas of mathematics and statistics including (among others) uncertainty quantification, topological data analysis, optimization, machine learning, causal inference, compressed sensing, and information theory to address important clinical and biomedical challenges. The goal of the program is the development of generalizable frameworks combining first principles, science-driven models of structural, spatial and temporal behaviors with innovative analytic, mathematical, computational, and statistical approaches that can portray a fuller, more nuanced picture of a person's health or the underlying processes.

Novel approaches for visualization, modeling, and analysis of biomedical data that meet the needs of a variety of audiences, from research scientists to the public, are essential to addressing the challenges posed by complex, heterogeneous data structures including images, text, networks, and graphs, unstructured data formats, nonlinear dependence structures, non-stationarity, missing information, and sparsity.