A key challenge for HBGDki is the aggregation of the vast amount of information scattered across literature to accelerate the construction of multidisciplinary influence models, which, in turn, impact the holistic understanding of child growth and development, and enable future research in this domain. For example, PubMed alone indexes more than 1 million publications per year. At this scale, assistance from computers through machine reading, can help researchers keep pace with current information.
Directed by faculty lead Mihai Surdeanu, researchers in the Computational Language Understanding (CLU) Lab at University of Arizona implemented a machine reading system that has the capacity to extract and aggregate influence relations at scale. For example, the current version of the tool has processed approximately 115 thousand open-access publications to construct a searchable database of over two million concepts relevant to children health connected by more than 2.5 million influence relations.
The above database can be searched for direct and indirect influence interrelations (e.g., how does the bacteria campylobacter indirectly influence malnutrition?). The subject matter experts can assemble the results of these searches into influence models that can be edited and shared.