Our research

The aim of our group is to facilitate the use of healthcare free-text (clinical notes, reports, letters) in medical research. Our research is founded on a number of key projects.

We will analyse anonymised data from brain scan reports to study the effect of brain appearance on future health.

We aim to compare machine and deep learning algorithms to rule-based methods for mining Scottish brain imaging reports.

We will apply NLP methods to generate a more comprehensive picture of patients and their health.

We aim to extend the phenotyping potential of disease status algorithms with linked health data and unstructured data from electronic medical records.

We focus on an exemplar study on linking routine neuroimaging assessments and electronic health records to identify the relationships between common physical and mental health conditions.