What is it about?
An increasing number of patients suffer from multiple diseases at the same time. This makes their treatment much more complex, and the standard medical treatment guidelines no longer apply (they are typically written for patients with just a single disease). We present computer-based techniques for analysing medical guidelines to detect how multiple guidelines may interact in unexpected ways, and how such adverse effects can be recognised and avoided.
Featured Image
Why is it important?
With our ageing population, we have an increasing number of patients that suffer from multiple simultaneious diseases. It's very difficult for doctors to be aware of all the ways in which the treatments for multiple diseases may interact in adverse ways, and have unexpected negative consequences for the patient. Our techniques exploit large knowledge-bases that are available on the Web of Data (Linked Data) to automatically detect and avoid such adverse consequences of interactions between multiple simultaneous treatments.
Perspectives
This is a very exciting paper for two reasons: it's exciting from a medical perspective because it helps doctors to detect unexpected interactions between multiple treatments; and it's exciting from a computer science perspective, because it shows the power of the very large linked open data knowledge bases that are now available on the semantic web.
Prof Frank van Harmelen
Vrije Universiteit Amsterdam
Read the Original
This page is a summary of: Inferring recommendation interactions in clinical guidelines1, Semantic Web, May 2016, IOS Press,
DOI: 10.3233/sw-150212.
You can read the full text:
Resources
Contributors
The following have contributed to this page
