Project AMIGO: Using graphs to help diagnose children with rare diseases
A Talk by Timm Amstein and Maaike Kusters
About this Talk
Utilizing AI for diagnosing patients rare-diseases is a huge challenge due to the lack of training data. This problem gets even more critical when the patients are children. Starting in Munich a collection of organizations with different backgrounds have decided to tackle the problem. By merging openly available research knowledge with the invaluable multiomics data of the patients in a graph, we are trying to build the basis for finding the needle in the hackstack through context knowledge.
To achieve this goals it is imperative to stay open for new ideas, facilitate collaboration, but at the same time keep the original data completely secret. The talk will provide a look at the challenge from the angle of data scientists, graph specialists, data architects, health care professionals and clinics. During the talk the interested audience will hear about our setup, our pipeline and the first advances on the road to find a way to help children with AI on graph.