Welcome to

What is CogStack?

CogStack is an application framework that allows you to extract information from unstructured data sources e.g. Electronic Clinical Records where majority of the information content is locked-up (i.e. not programmatically queryable) in multiple formats of unstructured data (i.e. binary word docs, PDFs, images, text fields etc). Once extracted, harmonised and processed, multiple uses of this unstructured data become possible based around information retrieval and extraction, these include Natural Language Processing (NLP), Enterprise Search, Alerting, Cohort Selection and Research.

NHS Foundation Trusts partners
million free text document deployed
million diagnostic results and reports

CogStack Ecosystem

Building data processing pipelines for documents processing with NLP using Apache NiFi and related services
Medical Concept Annotation Tool. A simple tool for concept annotation from UMLS/SNOMED or any other source.
Medical Concept Annotation Tool Trainer. A simple interface to inspect, improve and add concepts to biomedical NER+L -> MedCAT.
A Distributed, fault tolerant batch processing for Natural Language Applications and Search, using remote partitioning
Example deployment recipes based on CogStack

Latest News

Core Team

Richard Dobson
Group Lead
Amos Folarin
Software Development Lead
Kawsar Noor
Research Software Developer
James Teo
Clinical Lead
Angus Roberts
Natural Language Processing - NLP
Lukasz Roguski
Software Developer
Dan Bean
Clinical Informatics
Yamiko Msosa
Postdoctoral Research Systems Engineer
Tao Wang
Postdoctoral Research Associate
Zelko Kraljevic
Research Fellow
Tom Searle
Programme Manager and PhD student
Honghan Wu
Clinical Informatics
Alex Handy
Senior Research Fellow and Data Scientist


At King’s, a brilliant team led by Dr James Teo and Professor Richard Dobson have built a natural language processing tool called Cogstack. The Cogstack AI can perform manual coding and data collection tasks in a tenth of the time that it takes a human analyst. Technologies like these have potential to save millions in the cost of coding and analysing data.
Matt Hancock MP
Secretary of State for Health and Social Care
The team at King’s College Hospital NHS Foundation Trust and the South London and Maudsley Hospital tested CogStack for clinical coding in a fracture outpatient clinic setting to identify under-coding and was able to triple the depth of coding within a month (from ~10% of cases to 30% of cases having procedures recorded accurately). This translates to £1,260,000 of financial activity per annum even without the efficiency gains
Health data is key in getting it right for patients, but we’re not so good at the IT. CRIS, CogStack and automated systems support data collection and analysis can provide powerful evidence and very important for outcome measurement.
Matthew Hotopf CBE
Director of NIHR Maudsley BRC
Have a look at CogStack - big opportunities for these use cases at East Kent Hospitals once the electronic health record is in place.
Marc Farr
Chief Analytical Officer, East Kent Hospitals
Kullu Cecil and I are involved in work using historical data and current data to predict severe depression. Uses CogStack from King's College London and AI expertise from Liverpool Uni. Some early promising results. Looking for approvals to trial in clinical setting.
Jim Hughes
Strategic Advisor Digital Programmes, Mersey Care NHS Foundation Trust

Our Partners

© 2020 CogStack - PhiDataLab | Made by Suara