NEW YORK (GenomeWeb) – IBM and JDRF have announced a new collaboration to develop and apply machine learning methods to analyze decades of global type 1 diabetes (T1D) research and mark factors leading to the onset of T1D in children.
The partners said that the collaboration will create an entry point for T1D in the field of precision medicine, combining JDRF's connections to research teams around the world and its prowess in T1D research with IBM's technical capability and computing power.
"Never before have we been able to analyze [researchers'] data comprehensively, in a way that can tell us why some children who are at risk get T1D and others do not," JDRF president and CEO Derek Rapp said in a statement.
IBM scientists will examine at least three different data sets and apply machine learning algorithms to help find patterns and factors at play, with the goal of finding ways that could inhibit or prevent juvenile diabetes in children. Researchers plan to match variables and data formats and compare the differing data sets by leveraging previously collected data from global research projects.
Data analysis will examine genetic, familial, autoantibody, and other variables to create a foundational set of characteristics that are elements of all datasets. Models that the researchers produce will quantify the risk for T1D from the common set of features.
As a result, JDRF will be able to identify top predictive risk factors for T1D, organize patients based on top risk factors, and explore multiple data-driven models for predicting the emergence of diabetes.
Future phases of the collaboration may also consist of analyzing more complex datasets, such as microbiome and genomics or transcriptomics data.
"Each new [T1D] patient creates new records and data points that, if leveraged, could provide additional understanding of the disease," senior manager and program director of IBM's Center for Computational Health Jianying Hu said in a statement.
Hu added that the "deep expertise our team has in artificial intelligence applied to healthcare data makes us uniquely positioned to help JDRF unlock the insights hidden in this massive data set and advance the field of precision medicine towards the prevention and management of diabetes."