Sheffield scientists aim to pandemic-proof the NHS supply chain

New project to develop risk profiles for NHS suppliers could reduce the risk of future shortages of essential products and services during times of national crises
Many health and social care organisations reported having trouble procuring stocks of essential items to keep staff safe during first wave of COVID-19 pandemic
University of Sheffield scientists to create novel natural language processing methods to make wealth of supplier information accessible to NHS staff
System would help the NHS access wider market of suppliers and help procurement teams find reliable suppliers during post-Covid-19 recovery

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

University of Sheffield researchers are 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 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.

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.

The new project comes as the Government’s Health Secretary Matt Hancock was 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.

Over-reliance on a few healthcare suppliers and an increase in global demand contributed to the heavy shortages of PPE, essential equipment and pharmaceuticals within the NHS throughout the beginning of the pandemic in the UK.

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.”

The instant access to risk to the wealth of supplier data and risk profiles will make it easier for the NHS to respond quickly to the needs of its staff and access a wider supplier market, which will also include expanded access to small and medium sized enterprises (SMEs).

Dr Zhang, adds that: “Using NLP to consolidate NHS contracting data will create a platform that we hope can futureproof the NHS supply chain against any further crises like the COVID-19 pandemic; which saw health and social care organisations struggle to procure enough PPE and other important products and services to protect their staff and better serve patients.”

The marketplace will not only support the procurement of PPE, but provide access to suppliers of all healthcare related products, goods, consumables, services and outsourcing resources.

This applied research project aims to help the NHS mitigate the risks to its supply chain, by providing critical visibility into its evolving state, better preparing the NHS to identify and predict future potential procurement challenges during post Covid-19 recovery and any future national crises.

Dr Richard Freeman, CTO for Architecture and Data Science from Vamstar, said: “Using NLP, deep learning, big data and machine learning on our global marketplace data, with the NHS and EU contracting data, will create a supplier risk profile that is easier and more efficient for the NHS to manage its supply chain. It will mitigate the risk of future surges in demand for essential products and services by spreading demand over a wider number of suppliers. For hospitals and health systems such as the NHS, the pandemic demand and the overall shortages of essential supplies represented a monumental challenge.

“Going forward efficient supplier sourcing, supplier selection, and continuous supplier-risk assessment are the most critical tasks for any healthcare buyer and harnessing the technological advancements in artificial intelligence and the NLP expertise at the University of Sheffield will help us develop a platform to provide up to date, instant access to information about global healthcare suppliers, previously only available through laborious manual research.”

###

Additional information

The University of Sheffield

With almost 29,000 of the brightest students from over 140 countries, learning alongside over 1,200 of the best academics from across the globe, the University of Sheffield is one of the world’s leading universities.

A member of the UK’s prestigious Russell Group of leading research-led institutions, Sheffield offers world-class teaching and research excellence across a wide range of disciplines.

Unified by the power of discovery and understanding, staff and students at the university are committed to finding new ways to transform the world we live in.

Sheffield is the only university to feature in The Sunday Times 100 Best Not-For-Profit Organisations to Work For 2018 and for the last eight years has been ranked in the top five UK universities for Student Satisfaction by Times Higher Education.

Sheffield has six Nobel Prize winners among former staff and students and its alumni go on to hold positions of great responsibility and influence all over the world, making significant contributions in their chosen fields.

Global research partners and clients include Boeing, Rolls-Royce, Unilever, AstraZeneca, GlaxoSmithKline, Siemens and Airbus, as well as many UK and overseas government agencies and charitable foundations.

About Vamstar

Vamstar is changing the status quo in the healthcare industry and fully transforming the way healthcare supply chain functions, by building the very first SaaS-enabled AI driven B2B healthcare marketplace. Its platform is used for businesses and organisations connecting suppliers, such as pharmaceutical, medical device, and digital technology companies, with public and private buyers, such as hospitals, health insurances or Group Purchasing Organisations (GPOs). The company was founded in 2019 by Praful Mehta, Richard Freeman, and Vishesh Duggar with offices in the UK, India, the United States and Shortly Germany.

For more information, visit the company’s website at http://www.vamstar.io.

Published at Fri, 19 Mar 2021 00:11:15 +0000

SDSMT students use artificial intelligence, trying to pick perfect bracket

RAPID CITY, S.D. (KOTA) – There are 9.2 quintillion possible outcomes of the March Madness brackets. That is 18 zeros after the nine!

No one has ever verifiably picked a perfect bracket, but some students at the South Dakota School of Mines are hoping to be the first, with the use of an artificial intelligence technique.

“Guessing that is essentially impossible, you’ve got to use some sort of assisted educated guess,” said Trevor Bormann, a senior metallurgy and computer sciences student at SDSMT.

They are using a technique called neural networking that is similar to the way the nerves in the retina of our eyes process transmit information to our brains. Their bracket model utilizes basketball statistics and deep analytics, called KenPom, plus, attributes of all the teams to pick a winner.

“What we’re not doing, is we’re not picking individual games, per say,” said Dr. Kyle Caudle, a math professor at SDSMT. “The output of the neural network will predict how far a team will make it in the bracket.”

Not only are they using this season’s Ken Pom data, they are using information from years past.

“But we also use historical data,” s aid Dr. Randy Hoover, a computer science and engineering professor at SDSMT. “So, we use all the past brackets to train our neural network model. And so, we can look at teams from the historical data and see how far they’ve made it in the brackets, based on all of the statistics that they use.”

Past massive upsets actually help the modeling– take the #16 seed UMBC upset over #1 Virginia in 2018. Even though the outcome was so unlikely, the data point was added to the model.

“It basically helps it not fall in a pitfall because if you have our 20 years of data, and 1 always beats 16, it’s always going to prioritize that 1 seed over the other,” said Jackson Cates, a junior computer science student at SDSMT. “So it helps it not make a guarantee to pick that.”

“What are you guys doing with this model? Are you just using it to beat everyone in office bracket pools for the rest of your lives?” asked Anderley Penwell.

The four laugh and Bormann said they are competing.

“We’re using it to compete in a competition, called the MinneMUDAC Competition, where there’s a whole bunch of teams from around the Midwest area that are creating their own artificial intelligence and machine learning algorithms and competing to see who can get the best bracket,” said Bormann.

There are 9.2 quintillion possible brackets.

“If you took every single human on Earth, and conscripted all of them to fill out brackets, 24/7, and everyone completed a bracket a minute, it would take 2,500 years or so to finish all of them,” said Bormann.

Published at Thu, 18 Mar 2021 22:30:00 +0000