In the early months of 2021, the UK faced one of its most devastating waves of the Covid-19 pandemic. Following the surge in cases, Faculty collaborated with healthcare leaders to improve understanding of the effects of the virus in patients and open up new opportunities for AI in the medical field.
We collaborated with NHSX (a unit that supports digital innovation in healthcare, such as NHS artificial intelligence work), the British Society of Thoracic Imaging (BSTI) and Royal Surrey NHS Foundation Trust in a joint initiative to create The National COVID-19 Chest Imaging Database (NCCID).
Clinicians were struggling to meet the surging demand on hospitals due to limited understanding of Covid-19.
Chest scan images are a vital tool for researchers in the fight against COVID-19. However, siloed, incomplete datasets often make it difficult for researchers and developers to test new tools that could help improve the healthcare response to the disease.
The NCCID provides researchers and technology developers with managed access to a complete and representative sample of pseudonymised chest scans from suspected COVID-19 patients across the country. With this data, the NHS hopes to enable the development of software that can help doctors and researchers:
- Understand the impact and progression of the disease
- Assess the severity of the condition in individual patients
- Identify factors that may complicate recovery
- Prioritise patients whose condition is most likely to deteriorate
To help achieve this, Faculty provided the platform infrastructure, put in place processes that ensured the success of the NCCID and allows secure access to the data.
We fast-tracked the development of new NHS artificial intelligence tools by pioneering an AI infrastructure that eases strain on its resources.
We developed a secure, shared infrastructure (stored and owned by the NHS) that allows researchers and software developers access to the data they needed to develop new technology that can target COVID-19.
We then supported this infrastructure by establishing rigorous data management processes. They ensure the data is collected and accessed securely, efficiently and safely.
A separate dataset that’s used solely to validate AI models and never for model training was also created. In doing so, the infrastructure is able to help organisations address a key barrier to AI in healthcare:
With no firm, AI-specific guidelines currently in place, healthcare providers often have little assurance that their AI tool will deliver real, measurable results for practitioners and patients. Now, AI tools can be validated within the NCCID infrastructure platform to ensure that they are safe and effective for use in clinical settings.
Researchers or developers wishing to access the database and use the platform must have their requests assessed by a committee of scientific, technology, information governance and ethics experts. All of the scans in the library are stripped of any identifying patient details by each hospital trust before being submitted to the national collection, so that researchers only have access to pseudonymised information.
11 university consortiums use the database to create AI and healthcare tools that streamline Covid-19 treatment.
Dominic Cushnan, Head of AI Imaging at NHSX, said: “Applying the power of Artificial Intelligence to over 40,000 NHS scans is a fantastic opportunity to help us quickly detect disease patterns and treat patients with this new virus.”
The NCCID is now the biggest image library of its kind in the UK. It contains around 60,000 scans from 20,000 patients submitted by 22 organisations and NHS trusts. There are currently enough COVID-19 positive images to build a validation set that can ensure AI and healthcare tools currently in development meet the technical standards required for use in the NHS. This opens up new opportunities for machine learning in healthcare and crucially helps healthcare professionals save lives.
Teams from 11 British university consortiums are already using the NCCID to develop and test tools for the diagnosis, management and prioritisation of COVID-19 patients.