Electronic health records contain a rich history of the patient journey with huge potential for improving direct patient care, service delivery and research.
However, electronic health records can often be difficult to access and contain incomplete or unstructured information such as large amounts of text, which is challenging and time-consuming to analyse.
Around 80% of NHS patient data is locked in unstructured, siloed records, such as free text clinical notes, letters, discharge summaries or reports. Manual extraction is slow, costly, and error-prone, delaying insights and burdening staff.
How are we meeting this challenge?
The National Institute for Health and Care Research (NIHR) Biomedical Research Centre: Maudsley has led a collaboration with key partners including NIHR BRC: UCLH and King’s College Hospital to develop CogStack. Cogstack is a search engine, analytics and visualisation tool, and can unlock important data from electronic health records, with alerts to support clinical decisions and healthcare research.
CogStack can search any clinical data and, using our artificial intelligence (AI) and natural language processing (NLP), it can assign codes based on particular words, diagnoses or treatments. It operates within live NHS systems rather than as a standalone research tool, integrating with existing electronic health record platforms and secure data environments. This allows clinically meaningful information embedded in everyday documentation to be processed automatically and used as part of routine clinical, operational, and research workflows. This represents a qualitative shift rather than an incremental improvement. Tasks that previously required manual review of thousands of records, or were simply not attempted due to scale, became routine and repeatable.
This short video describes how CogStack implements best-of-breed enterprise search, NLP, analytics and visualisation technologies to unlock the health record and assist in clinical decision making and individual direct patient care.
CogStack integrates with hospital electronic health record systems such as Epic in South London and Maudsley NHS Foundation Trust and national initiatives like NHS Sub-National Safe Data Environments, enabling multiple benefits to:
- Patients: Fewer missed diagnoses, safer care pathways (for example, reduced “lost-to-follow-up” incidents).
- Clinicians: Reduced administrative workload, actionable insights via alerts or dashboards.
- NHS: Cost savings (such as streamlined workflows), and interoperable data for research.
- Researchers: Access to structured, searchable datasets (for example, more than 1 billion SNOMED annotations from SLAM records).
Collaboration and achievement
CogStack, developed by the NIHR BRCs: Maudsley and UCLH with Guy’s and St Thomas’, King’s College Hospital, UCL and King’s College London, leverages AI and NLP to harmonise unstructured data across the health system.
CogStack has collaborated with NIHR Applied Research Collaboratives (ARCs), NHS AI Lab, and NIHR Mental Health Mission/TRC to accelerate trial recruitment, for example its use led to recruitment that was eight times faster for COVID-CNS project.
The freely accessible and secure CogStack platform has been deployed in local NHS Trusts at King’s College Hospital, South London and Maudsley NHS Foundation Trust, Guy’s and St Thomas’, and University College London Hospitals, triggering lasting change for both physical and mental healthcare.
It has since expanded its reach and has been deployed in 16 NHS Trusts and 3 Sub-National Safe Data Environments (SDEs) including commercial and community adaptations and expanding its footprint globally including new partnerships established with NHG Group & SingHealth in Singapore.
International health and care providers and academic groups, including Monash Partners Academic Health Science Centre, Australia who were awarded AUS $1.92million for local deployment, have adopted the system.
Looking to the future
The goal is to expand to all NHS Trusts, NHS England’s SDEs and new National Data Service, providing AI-based NLP text structuring (annotation) services using existing models.
The team would like to use CogStack to help tackle inequalities through identifying biases from audits, for example inequalities in delays to dementia diagnosis.
In 2025, CogStack formally launched as a university spinout and there are also plans to scale revenue models (for example, automated coding, life science partnerships). CogStack Ltd will develop the technology further and deploy it at scale across health and care organisations in United Kingdom, Europe, Asia & Australia.
Impact
- Enhanced data efficiency and savings of £1.2m per year in 2018 for King’s College Hospital by detecting thousands of missing records of fracture clinic procedures in only 30 minutes.
- Accelerated medication reviews which saved more than two hours of work per pharmacy review at South London and Maudsley NHS Foundation Trust using CogStack AI to read and summarise records.
- Improving patient safety at University College London Hospitals NHS Foundation Trust by providing alerts for patients who are ‘lost-to-follow-up’ in their healthcare journey, identifying hundreds of such events to be actioned in the gastroenterology clinic.
- Increased trial eligibility yield from 0% to 10.9%, while reducing clinician workload (NASA-TLX) by 22%, in the STOP’EM (Surgeons Trial Of Prophylaxis for Epilepsy in seizure naive patients with Meningioma) randomised controlled trial at UCL.
-
CogStack NLP revealed significant under-representation of women, ethnic minority groups and socioeconomically disadvantaged patients in coronary artery disease (CAD) clinical trials, compared with the wider CAD patient population.
References
Awards
