Through the MS-PINPOINT programme, routine brain and spinal cord MRI data from more than 7,000 patients and over 40,000 scans have been securely retrieved and anonymised from UCLH archives dating back to 2010. These imaging datasets are linked with anonymised structured and unstructured clinical data.

This SAFEHR-enabled infrastructure supports the development and training of next-generation machine learning and prognostic models designed to improve prediction of disease progression, treatment response, and long-term outcomes in MS.

Federated AI model training is now underway across the 13 participating hospitals within the international MS-PINPOINT consortium, including sites in the United Kingdom, the Netherlands, and Canada.

In collaboration with the CogStack, ARC, and SAFEHR teams, additional pipelines have also been developed to digitise and process historical scanned clinical reports into machine-readable research data. This has extended longitudinal follow-up by more than 10 years for many patients, substantially strengthening the dataset for AI model development and translational research.