Electronic Medical Records for Research-Tackling Unstructured Data

Angus Roberts (Life Science Lead forGATE ,Sheffield University) & Dr. Robert Stewart (Clinical Informatics Lead, NIHR Biomedical Research Centre at South London and Maudsley NHS Foundation Trust & King’s College London) spoke about extracting structure from free text and using open source toolkits to do it, in particular UIMA and GATE (see this article on combining UIMA and GATE) – of note, training is available for the latter – as the GATE guys put it :”coaxing state-of-the-art performance (accuracy, speed) from these tools is still a fine art, and likely to remain so” – so a little training might come in handy.

In talking about the language engineering skills required to make effective use of these tools and the creation of pattern suites, the question which formed for us was “are you going to make the pattern suites you created for clinical data mining publicly available in pattern libraries?” We’ll get back to you when we have an answer. The abstract for their talk follows:

The South London and Maudsley NHS Foundation Trust Biomedical Research Centre (SLAM BRC) hosts Europe's largest psychiatric case register. This is updated daily from live electronic medical records, and made available to approved researchers via a clinical records interactive search system (CRIS): a web search interface, and other search tools. While the structured records in the case register are of great value, an estimated 80% of the value of the data lies in free text entries made by clinicians in day-to-day practice.

With over 180,000 records, automated information extraction or text mining is essential if we are to make use of this. GATE - a General Architecture for Text Engineering’ - has been integrated with CRIS, to give a text mining capability. Several GATE applications have already been built to extract specific variables from free text. Output from these applications is being used successfully in a number of research projects, and a number of new applications are currently under development. There is an increasing understanding of how to maximise the benefits of GATE given the particular characteristics of the data.”

NIHR / NOCRI Information Systems Workshop - Part 1

With apologies for the delay in getting this to you, here comes the first of our updates on last Monday's NIHR Office for Clinical Research Infrastructure (NOCRI) Information Systems Workshop!

The workshop was held at Guy's Hospital and the introductory remarks began with a welcome from Professor Simon Lovestone, who is, in addition to being the Director of the Mental Health Biomedical Research Centre at South London and Maudsley & King's College London, Director of Research at King's Health Partners Academic Health Sciences Centre.He was followed by Mark Samuels (MD, NOCRI) and Peter Knight who is now Deputy Director of R&D and Head of Research Information and Intelligence at the Department of Health.

Session 1 - Chair: Prof. Peter Parker, Cancer Theme Lead, NIHR BRC at Guy's and St. Thomas' NHS Foundation Trust & King's College London.

We've blogged twice before about Mike Denis's presentation covering South London and Maudsley NHS Foundation Trust's (SLaM) Clinical Records Interactive Search (CRIS) system - Mike was up first in the first session after the introductory messages and talked on the Vision for Translational Informatics at SLaM.

He talked to two themes in relation to SLaM's creation of a Personal Health Record, the first being the technical aspects (including deep pseudonymisation - meaning that it extends into the free-text within records) and the second being the social aspect that puts the patient in the driving seat of the process but also aims to link Patient Reported Outcomes to research.

An interesting aspect of the technical discussion was the use of intelligent agents to provide automated analysis and predictive analysis - which chimed with Prof. Michael Luck's comments later in the day on the use of computer sicence agents in medical informatics - of which more later.

Mike emphasised the scalability of the approach, the potential to implement it across multiple centres and carry out data linkage inter-organisationally.

Here's the abstract provided for Mike's talk:

“Within SLAM, we have sought to focus on a relatively fine-grain model of clinical informatics, building the Clinical Records Interactive Search (CRIS) system which provides researchers access to full but anonymised data on a large mental health NHS provider covering a 1.2m population catchment area and containing over 180,000 case records. Key areas for resource development which will be outlined include the routine collection of consent for researcher contact, informative data linkage with internal (biological) and external (health and social) data resources, and adding depth to the dataset through natural language processing, shared health records and patient reported outcomes. We believe that these developments, coupled with advances in nested trial designs and electronic health records (EHR) feedback loops will help move the current focus of EHR and 'case register' research in our field from an observational to translational footing.”