OptimalAI
Cambridge University Hospital
NHS
Creating the UK's national COVID-19 database to support development of AI to help patients with COVID-19
AI Product Governance
The OptimalAI team has - for many years. - led the clinical trial management, governance and validation of multiple AI products for the NHS.
NHS AI Lab
The OptimalAI team has supported the NHS AI Lab since its inception.
About the NHS
The The National Health Service (NHS) is United Kingdom's publicly funded healthcare system. It is one of the largest single-payer healthcare systems in the world. The NHS AI Imaging department develops and supports AI that increases the speed and accuracy of diagnosis and ensure the most beneficial solutions for patients.
Objective
Our team worked with the imaging team at the NHS AI Lab to develop and support the AI systems that create human-centric route to getting the best AI into use in the NHS.
NCCID
The OptimalAI team worked with the imaging team at the NHS AI Lab to develop the National COVID-19 Chest Imaging Database (NCCID). The NCCID is a centralized UK database of thoracic imaging and corresponding clinical data to support the development of machine learning tools focused on improving care for patients with a severe COVID-19 infection.
The NCCID provides high-quality DICOM images acquired from a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage.
The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.