Clinical Natural Language Processing Research Group

Group members

Our group includes medical, epidemiological, computer science, and computational linguistics researchers from the Usher Institute and School of Informatics.

Group leaders

Our group is led by Dr Honghan Wu and Dr Beatrice Alex.

Dr Honghan Wu

Honghan is a Rutherford Research Fellow funded by MRC/HDR UK. His research involves the application of text technologies and Knowledge Graph techniques to analyse EHRs. The goal is to derive a consistent and comprehensive patient phenome from unstructured and structured EHRs and provide semantic computation upon it to support decision making for tailored care, trial recruitment and research.

Dr Honghan Wu

Dr Beatrice Alex

Beatrice Alex is Chancellor's Fellow and Turing Fellow at the University of Edinburgh.  Her research is on applying text mining methods to data sets in different domains including electronic healthcare records as well as historical text collections.

Dr Beatrice Alex

Clinical leaders 

Professor Ewen Harrison

Ewen is Professor of Surgery and Data Science at the University of Edinburgh and a Consultant HPB and Transplant Surgeon at the Royal Infirmary of Edinburgh. His research interests include crowd-sourcing patient-level date, surgical trials, mobile data collection platforms and "wearables", automated data processing and display, natural language processing/sentiment analysis, decision modelling, Bayesian statistics, administrative data analysis, and patient reported outcomes.

Professor Ewen Harrison

Dr William Whiteley

Dr Will Whiteley
Will is a Scottish Senior Clinical Fellow (funded by CSO) in the Centre for Clinical Brain Sciences, University of Edinburgh. His work seeks to elucidate the mechanisms for prevention of disability due to stroke and dementia through the design, delivery and analysis of epidemiological studies and clinical trials. Of particular interest to him is the better use of large electronic health record datasets for more efficient clinical trials and cohort studies.

Dr William Whiteley

 Other members

Archie Campbell

Archie is the Data Manager for the Generation Scotland biobank, with a background in systems analysis and programming. He is responsible for liaising with researchers to give them access to the biobank's resources, with expertise in using medical records for research.

Generation Scotland

Dr Arlene Casey

Arlene is a research fellow funded by the Alan Turing Institute within the Literatures, Languages and Cultures School, University of Edinburgh. She is interested in developing natural language processing and machine learning techniques, specifically for discourse understanding and information retrieval. Her recent PhD work has focused on building models of expected content within scientific articles, through mixed-method user studies, and understanding how language technology can be applied to recognise and retrieve this information to support PG students in writing Related Work sections.

Dr Emma Davidson

Emma is a Public Health clinician with interests in data science, chronic disease prevention, and health inequality. She is a Clinical Research Training Fellow in the Centre for Clinical Brain Sciences and is undertaking a PhD looking at the automated processing of brain imaging reports to identify simple brain phenotypes that increase dementia risk.

Dr Emma Davidson

Dr Hang Dong

Dr Hang Dong
Hang is a Research Fellow (funded by HDR UK) in the Centre for Medical Informatics, Usher Institute. He is working on applied machine learning, natural language processing (NLP), and data mining for phenotyping from electronic health records.

Dr Hang Dong

Robin Flaig

Robin is the Operations Manager for Generation Scotland and is responsible for maintaining current data linkages and expanding new ones. She also works with Archie Campbell to provide access to researchers to the GS biobank resource.

Generation Scotland

Andreas Grivas

Andreas's research is on applied machine learning (ML) for natural language processing (NLP). He has extended EdIE-N, a neural network based text mining system for analysing radiologists' brain imaging reports (MRI and CT scans).

Andreas Grivas

Dr Claire Grover

Claire's research is in linguistics and NLP, with a focus on the syntactic and semantic analysis of text. She is the main author of EdIE-R, a text mining system for analysing radiologists' brain imaging reports (MRI and CT scans).

Dr Claire Grover

Aidan Hutchison

Aidan is Database Designer, Developer and Consultant in the Centre for Medical Informatics, Usher Institute.

Dr Grant Mair

Grant is Senior Clinical Lecturer (funded by the Stroke Association) and Honorary Consultant Neuroradiologist in the Centre for Clinical Brain Sciences, University of Edinburgh and NHS Lothian, respectively. Grant's work aims to improve our understanding and use of brain imaging biomarkers in patients with stroke both for clinical trials and routine practice.

Dr Grant Mair

Dr Michael Poon

Michael is a neurosurgeon interested in epidemiology and data science. His research focus is on brain tumours and haemorrhages. He is undertaking a PhD to determine predictors of treatment response in patients with gliomas - a type of brain tumour.

Dr Michael Poon

Dr Víctor Suárez Paniagua

Víctor is a Research Fellow funded by the Health Data Research UK in the Centre for Medical Informatics, Usher Institute of the University of Edinburgh. His research is on machine learning, with an emphasis on deep learning, for natural language processing in order to extract relevant information from medical documents accurately.

Professor Catherine Sudlow

Cathie is a clinical neurologist and epidemiologist and Director of HDR UK’s British Heart Foundation Data Science Centre. Her clinical work involves assessing and treating patients with suspected acute stroke (or ‘brain attack’) in the hospital emergency department. Her research interests have always been firmly embedded in the world of big data, with a focus on large scale, collaborative, open science efforts to understand the causes (in our genes, environment and lifestyle), detection, prevention and treatment of major diseases, especially those that affect people in middle and older age.

Professor Catherine Sudlow

Richard Tobin

Richard’s research is in NLP and he has worked on text mining in various domains. He developed the LT-XML2 toolkit for NLP, which is used in the EdiE-R and EdiE-Viz pipelines.

Richard Tobin

Dr Heather Whalley

Heather is a Senior Research Fellow in Neuroimaging at the Centre for Clinical Brain Sciences at the University of Edinburgh. Her main area of research is based on understanding how causal risk factors contribute to psychiatric disorders. This includes linking routinely collected healthcare data (including imaging) with mental health data to identify relationships between common physical and mental health conditions.

Dr Heather Whalley

 

Alumni

Dr Daniel Duma

Dr Philip Gorinski