AI-driven dataset to reveal new insights around diabetes

New York (The Uttam Hindu): In a first, a team of scientists has introduced a flagship AI dataset from a study of biomarkers and environmental factors that might influence the development of type 2 diabetes.Since the study participants include people with no diabetes and others with various stages of the condition, the early findings hint at a tapestry of information distinct from previous research, according to the report published in the journal Nature Metabolism. “We see data supporting heterogeneity among type 2 diabetes patients — that people aren’t all dealing with the same thing. And because we’re getting such large, granular datasets, researchers will be able to explore this deeply,” said Dr Cecilia Lee, a professor of ophthalmology at the University of Washington School of Medicine in the US. For example, data from a customised environmental sensor in participants’ homes show a clear association between disease state and exposure to tiny particulates of pollution.

The collected data also include survey responses, depression scales, eye-imaging scans and traditional measures of glucose and other biologic variables.“All of these data are intended to be mined by artificial intelligence for novel insights about risks, preventive measures, and pathways between disease and health,” the authors noted. The aim is to gather health information from a more racially and ethnically diverse population than has been measured previously, and to make the resulting data ready, technically and ethically, for AI mining.

“This process of discovery has been invigorating. We’re a consortium of seven institutions and multidisciplinary teams that had not worked together before. But we have shared goals of drawing on unbiased data and protecting the security of that data as we make it accessible to colleagues everywhere,” said Dr Aaron Lee, also a UW Medicine professor of ophthalmology and the project’s principal investigator.Hosted on a custom online platform, the data are produced in two sets: a controlled-access set requiring a usage agreement, and a registered, publicly available version stripped of HIPAA-protected information.