A paper entitled ‘Deployment of a Free-Text Analytics Platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals’ has been published in JMIR Publications, detailing the implementation of the technology and how it has been used to facilitate clinical research and service evaluation projects.
The paper notes that working with electronic health records (EHRs) presents challenges in “harmonising and accessing the hospital’s entire record from both existing and legacy data systems”; another challenge is “having tools and techniques available to mine and extract data from within these records, especially the unstructured free text”, along with the interpretation of the free text.
The CogStack platform has been developed to address these problems and is described as an “information retrieval system designed to interface with a hospital’s EHR system”.
The paper explains how CogStack was deployed at University College London Hospitals (UCLH) and has to date processed over 30 million records, with the insights produced informing a number of clinical research use cases.
It goes on to describe a number of the research and evaluation projects that the platform has been used for. These include clinical trial recruitment; natural language processing (NLP) at the point of care to allow clinicians to generate structured information from their clinical notes; creating detailed analysis of adverse reaction reports submitted to the national incident reporting database; improving the clinical referral process for neurology clinics; producing better structured data for the ear, nose and throat clinic; working along the clinical coding team to build an interface to speed up the coding workflow; identifying clinical intent in free-text notes; and building a pipeline to analyse hospital discharge summaries and identify individuals with atrial fibrillation who are taking suboptimal medication.
The paper concludes that the platform “enables the hospital to unlock important clinical information from the unstructured portion of the record”, with the authors adding that they would recommend CogStack’s deployment in “most research-focused health care organisations” due to the way it has supported a wide range of clinical use cases, and due to its low-cost requirements.
View the paper here: Noor K, Roguski L, Bai X, Handy A,Klapaukh R, Folarin A, Romao L,Matteson J, Lea N, Zhu L, Asselbergs FW, Wong WK, Shah A, Dobson RJ, Deployment of a Free-Text Analytics Platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals, JMIR Med Inform 2022;10(8):e38122.