Research Interests

My current projects include:

  • intelligent use of health data for epidemiology and clinical care, big data, linked data;
  • text mining of the medical record, tackling an important and underused source of health data;
  • social media, sensing, control and mobile health, Internet of Things;
  • knowledge representation, terminologies and ontologies;
  • the translation of research software to real world, production settings;
  • research infrastructures.
I have an interest in many other areas of health informatics research: clinical information systems, medical knowledge representation and management, medical records, public health information, computational imaging, telemedicine, genomics, and pharmacoinformatics.

Current funding

  • OpenMinTeD, open mining infrastructure for text and data, an EC Horizon 2020 E-Infrastructure project.
  • KConnect, search technologies for medical information, an EC Horizon 2020 project.
  • NIHR BRC-MH. A long-standing collaboration over several projects, with the NIHR Biomedical Research Centre (BRC) for Mental Health, which is run jointly by the South London and Maudsley NHS Trust, and King's College London Institute for Psychiatry.


Some projects I am, and have been, associated with. Dates give years of my involvement, which might not be the project lifespan.

OpenMinTeD Text and data mining infrastructure, an EC Horizon 2020 project Principal investigator 2015 - 2018
KConnect Search technologies for medical information, an EC Horizon 2020 project Principal investigator 2015 - 2017
NIHR BRC-MH Text mining service contract for the National Institute for Health Research Biomedical Research Centre for Mental Health Sub-contractor 2010 - 2017
GATE General Architecture for Text Engineering: a leading toolkit for text mining Lead, life sciences 2007 - present
E-HOST-IT Supporting role for Dr. Rina Dutta at King's College London, for an Academy of Medical Sciences Clinical Scientist Fellowship, Electronic health records to predict Hospitalised suicide attempts: Targeting Information Technology solutions Sub-contractor
E-CHASM Supporting role for Dr. Jayati Das-Munshi at King's College London, for an Academy of Medical Sciences Clinical Scientist Fellowship, Ethnicity and Cardiovascular Health inequalities in Severe Mental illness Sub-contractor
FastVac Fast production of successful vaccines, contributing text mining support for systematic literature reviews, contracted via Public Health England and Food and Environment Agency Sub-contractor2012 - 2014
Khresmoi Medical information analysis and retrieval, an EC Framework 7 project Co-investigator 2010 - 2014
TextVRE Infrastructural support for the complete lifecycle of research in e-humanities textual studies Principal investigator 2009 - 2011
LarKC The Large Knowledge Collider, a platform for massive distributed incomplete reasoning, an EC Framework 7 project Researcher 2008 - 2011
CLEF Clinical E-Science Framework Researcher 2002 - 2008
Geodise Grid Enabled Optimisation and Design Search for Engineering Researcher 2002
myGrid myGrid - directly supporting the e-scientist Researcher 2002
openGALEN Advanced open terminology for clinical information systems Researcher 1999 - 2002
topThing Medical ontology services and software Researcher 1999 - 2002
Prescribing Indicators Feasibility and reliability of computerised review of long term prescribing Researcher 2000 - 2002
Telenurse ID-ENTITY: CompET Experimental compositional entry tool for the Telenurse nursing informatics project Researcher 2000
Radiology Workbench An integrated system for radiology reporting Researcher 1999 - 2002
Drug Ontology A highly structured drug knowledge base (PRODIGY Phase 3 GP guidance system was the initial application) Researcher 1999 - 2001
SynEX Synergy of medical records on the extranet Researcher 1999 - 2000
Clinical Terms (The Read Codes) The UK standard clinical terminology Consultant 1998 - 1999