NImRLS

“You have to see the data from large-scale health studies as a gold mine”, says Dr. Federico Raimondo: “We know there is a lot of gold in there, but we have to find it first!” Through this HIP project, the computer specialist and colleagues aim to tap more effectively into the existing troves of data. “The biggest challenge is in making these gigantic amounts of data manageable.”

The team aims to blaze a trail through the data in a concrete case study. Their subject is restless leg syndrome (RLS), which is behind many severe sleep disorders and forms of depression. Research has already identified many of the genes implicated in this widespread disorder, but there is not enough linking the physical manifestations in the brain to the genetic basis so that those manifestations can be used as biomarkers in diagnosing the condition. Large-scale health studies have databases that hold both types of information – brain scans and genomic data – on each individual patient.

The task is now to connect the two. “We are searching though patient brain scans for structures that are typical for this syndrome,” Federico Raimondo says. The team can draw on data from the UK Biobank, for example, which currently stores data and images from more than 40,000 participants. The aim of the project is to organise these volumes of data so that machine learning systems can sift through them for relevant connections. The information delivered is expected to be highly useful in health research overall, since the highly complex data analysis software should be portable to other fields of medical research.