University aims to pandemic-proof the NHS supply chain

A platform to help the NHS order essential supplies, such as PPE from low-risk suppliers, could ease future shortages like those experienced in the first wave of the pandemic.

This is according to researchers from the University of Sheffield, who have been working with Vamstar, the world's first artificial intelligence (AI) powered healthcare marketplace, to create a data-driven platform that can analyse the wealth of NHS and global procurement data from previous supply contracts and allow NHS buyers to evaluate the credibility, and capability of suppliers to fulfill their order.

The project aims to diversify the NHS supply base and reduce the overall risk of the NHS purchasing from companies who may be unable to fulfill an order and of receiving sub-standard goods. Its launch follows Health Secretary Matt Hancock being criticised for rejecting claims that there was a national shortage of PPE during the first wave of the pandemic, despite many health and social care organisations having reported difficulty acquiring sufficient stocks of essential PPE to keep staff safe.

The platform will give a real-time risk-rating to each supplier, including information about the goods and services they supply, the quality, and their history of working with the NHS and other EU hospitals. Scientists from the University of Sheffield Information School are developing novel Natural Language Processing (NLP) methods for the automated reading and extraction of data from large amounts of contract tender data held by the NHS and other European healthcare providers.

They will work with Vamstar to incorporate this wealth of information into a healthcare procurement marketplace which will make it accessible for NHS procurement teams instantaneously for the first time.

Dr Ziqi Zhang will lead the team at the University of Sheffield developing the novel NLP methods. He said: “Currently, procurement and tender data stored in various digitised documents isn't readily available centrally to NHS procurement teams for analysis when ordering stock.

“Supplier selection during the procurement process is an extremely slow and laborious process for NHS buyers and involves manually locating, reading, and analysing a significant amount of such data from various sources in order to evaluate a supplier's capacity and credibility.

“NLP involves a series of techniques for the automated analysis of a variety of documents, to enable the efficient retrieval and consolidation of relevant data for procurement and we will develop novel healthcare NLP models for this research project.”