CogStack enables healthcare staff to analyse clinical data using AI to draw insights from documents in any format in electronic health records. The multidisciplinary team behind CogStack includes computer scientists, clinicians and researchers from ARC South London’s applied informatics theme.
In The Sudlow Review, published in November 2024, Professor Cathie Sudlow asserts that in many areas the UK is a global leader in the transformational use of health data for public benefit, yet our complex and inefficient data systems make it difficult and slow to conduct research which can bring greater benefits to patients.
“We are letting patients and their families down and no change is not an option,” Professor Sudlow says.
Referencing CogStack’s ability to extract structured information from unstructured clinical text, the report recommends:
…that the Department of Health and Social Care (DHSC) should invest in the efficiency gains of deploying tools to securely access and extract structured information from unstructured medical free text across all primary and secondary care Electronic Patient Records systems.
CogStack was developed by researchers at King’s College London (NIHR Maudsley Biomedical Research Centre), King’s College Hospital, Guy’s and St Thomas’ and South London and Maudsley NHS Foundation Trusts, University College London and NIHR University College London Hospitals Biomedical Research Centre. Cogstack has recently expanded beyond these founding institutions and is now being adopted across the NHS.
CogStack’s advanced natural language processing and machine learning capabilities are designed to address many of the challenges highlighted in the review, particularly in extracting valuable insights from unstructured clinical data. We’re excited about the potential impact of these recommendations on accelerating research, improving patient care, and driving innovation in the UK healthcare system.