Developing Semantic Methods to Learn from Healthcare Data

Add to your list(s) Download to your calendar using vCal

• Dr. Luke Slater, Gkoutos group, Centre for Computational Biology
• Wednesday 20 October 2021, 12:00-13:00
• Haworth Building Room 320A and Online.

If you have a question about this talk, please contact Dr. Marc Haber.

Electronic Healthcare Records (EHRs) contain a wealth of information concerning biomedical entities, such as drugs, patients, diseases, equipment, and more. Spanning multiple modalities such as text, structured, and other semi-structured data, the challenges of integrating and therefore utilising these data for secondary research are great. Biomedical ontologies link instances of entities with each other, and with a rich font of background knowledge and contextual understanding. By building semantic representations of healthcare entities, we enable methods that utilise these representations to produce insight. In this lecture, we will discuss the development and application of novel semantic methods for extraction, characterisation, and classification using EHR data, with a focus on textual data, to answer clinically relevant research questions. We will also discuss application of these methods to social media data, literature, and patient voice, building representations of diseases and associated concepts across multiple domains, which can then be contrasted to gain insight into how knowledge, expression, and priorities for healthcare differ between them.

This talk is part of the CCB seminars series.

This talk is included in these lists:

• Haworth Building Room 320A and Online

Note that ex-directory lists are not shown.