Nvidia rolls out AI platform across NHS hospitals

Nvidia has partnered with ten National Health Service (NHS) Trusts to roll out its AI platform across UK hospitals.

The AI Deployment Engine (AIDE) platform will provide AI-enabled disease detection tools to healthcare professionals to help them diagnose and treat cancers, dementia, strokes, and other conditions.

It’s currently being deployed at Guy’s and St Thomas’s, King’s College Hospital, East Kent Hospital University, and University College London Hospitals NHS Foundation Trusts, where it will serve 5 million patients a year.

A total of 11 NHS hospitals are expected to be using the platform by the end of 2023, raising the number of patients served to 18 million.

The new platform will help clinicians have more information about their patients, aiming to make the data about their health more accessible and interoperable, and meet the ultimate goal of improving patient care.

Nvidia's AI platform is built on MONAI, an open source medical imaging AI framework co-developed by Nvidia and the AI Centre for Value Based Healthcare, a group of hospitals, universities, and partners.

The chip giant said that MONAI helps reduce the complexity of medical workflows and aids developers in building and deploying AI applications.

Using the framework has enabled clinics to more easily interpret medical exams and discover more information about patients. In the UK, MONAI is currently used by Guy’s and St Thomas’ Hospital and King’s College Hospital due to its ability to streamline AI model building.

“Deployment of this infrastructure for clinical AI tools is a hugely exciting step in integrating AI into healthcare services,” said James Teo, professor of neurology and data science at King’s College Hospital NHS. “These platforms will provide a scalable way for clinicians to deploy healthcare AI tools to support decision-making to improve the speed and precision of patient care. This is the start of a digital transformation journey with strong, safe and open foundations.”

“Across the healthcare ecosystem, researchers, hospitals, and startups are realising the power of incorporating a streamlined AI pipeline into their work,” said Haris Shuaib, AI transformation lead at the AI Centre. “The open-source MONAI ecosystem is standardising hundreds of AI algorithms for maximum interoperability and impact, enabling their deployment in just a few weeks instead of three-to-six months.”

Currently, the AI Centre has developed algorithms to improvise COVID-19 diagnosis, brain tumours, breast cancer, dementia risk, and stroke detection.

AIDE is able to connect AI algorithms, that have been approved, to a patient’s medical record, and the data never leaves the hospital trust, according to Nvidia. Once analysed, the data is sent back to the electronic healthcare record.

Nvidia also revealed that AIDE's will be open sourced and is set to be published to GitHub on 7 December 2022.