Consortium led by Vamstar wins funding to build world’s largest healthcare supply chain network using AI

Vamstar, the data science based global B2B healthcare and life sciences marketplace, wins Innovate UK funding to create the largest healthcare and life science supply chain network with the University of Sheffield and University of Nottingham.

London, May 7th, 2021  -– Vamstar, the data science based global B2B healthcare and life sciences marketplace, the University of Sheffield, and University of Nottingham are building the world’s largest supply chain network globally, interconnecting buyers and suppliers across the healthcare and life sciences industries by products, services, and devices.

In 2019, 44% of healthcare contracts within the European Union received just one applicant, and 15% had no bidders at all, costing the taxpayer billions in wasted critical healthcare resources. Supplier selection, management, and overall procurement process in the health sector is a dated/complex manual process leading to incoherent supply-demand matching and poor supply chain visibility.

Moreover, in times of crisis like the COVID-19 pandemic, where there is a sudden surge in global demand for critical supplies, the apparent flaws and inefficiencies of the current healthcare marketplace are accentuated and expose the buyers to significant supply risks. Furthermore, the global supply chains are affected by the legal and policy environment that they inhabit.

In turn, establishing a dynamic, real-time connected mapping of global supply chains and the networks that get constantly created therein can inform policy making by identifying the most suitable policy permutations and thus optimise policy outcomes.

There is a critical need for an e-marketplace in healthcare that focuses on (1) improving visibility of supply/demand data that are currently heterogeneous or inaccessible; (2) giving access to all suppliers and buyers, allowing capturing of the long tail of SMEs in the procurement mix; (3) allowing effective and efficient supply chain management to enable connected performance tracking and measurement of the procurement relationships; and (4) allowing a lens to gauge the market to inform policy making for the new industrial landscape.

Doing this manually at a global scale for all healthcare products, services, and features is not possible. There is a need for an automated tracking and monitoring solution for capturing all the connections and activities in the healthcare supply chain, which can make matches and predictions, so the buyers and suppliers have complete visibility on the marketplace. With the emergence of big data, deep learning, and graph analytics, this is possible.

Understanding buyer and supplier connections through their purchasing habits of healthcare product and service groups reveals behavioural patterns over time that can be used for enhanced insights, optimised predictions and complex matching in the backend systems.

Subset of Vamstar’s Supply Chain Network generated using AI,  showing the complexity in relations between healthcare suppliers and hospitals

“The initial network pilot on existing Vamstar data shown in the visualisations above required us to leverage the scalable compute and storage power of AWS due to the sheer size of the data and complexity in relationships. Specifically graph database Amazon Neptune, big data processing using Amazon EMR and massively parallel processing data warehouse Amazon Redshift which we will elastically scale-out on AWS to deal with full data we are planning to use.” commented Richard Freeman, PhD, co-founder and CTO of Architecture and Data Science at Vamstar.

To make this possible we joined the startup AWS Active Programme that provides the support, resources and training we needed.

“AWS is proud to be associated with this project that has been funded in part through the AWS Activate program which provides many benefits to startups including training and support access, as well as up to $100,000 in AWS Activate Credits. We look forward to seeing how this innovative approach to tackling complex issues in the healthcare and life sciences marketplace evolves, and are excited to be a part of this journey.” commented Chris Hayman, Director, UK Public Sector, Amazon Web Services (AWS).

The existing underlying network was created using in-house complex natural language processing (NLP) and Machine Learning models, including Nvidia GPUs for training our custom deep learning NLP models.

During the project and in collaboration with a team lead by Dr Ziqi Zhang from the University of Sheffield, global leaders in NLP, we will be scaling out both in terms of data sources we process and in terms of the nodes and relationships represented in the network, allowing us to meet the complex supply chain objectives of the project.

“NLP involves a series of techniques for the automated analysis of a very large amount of documents, to enable the efficient retrieval and consolidation of relevant data for the healthcare supply chain. It will allow the extraction of supply chain data points representing hospitals, suppliers, and products and services, and the connection of these data points based on complex relationships mined from various data sources such as tender and contracts.” Dr Ziqi Zhang, Lecturer and expert in NLP and Text Mining, University of Sheffield. 

Why Networks and not Database Tables?

Complex marketplace relationships are hard to represent in a traditional relational model. For example, think about how LinkedIn connections are represented as 1st, 2nd and n-degree relationships. Useful insights that can be derived from your degree of separation for your customers, connections with colleagues, their skills, linked organisations, and schools all overlayed with the time dimension. Now imagine you included all the products and services each organisation offers, too that is similar to what we are doing.

“At Vamstar, we are representing a healthcare marketplace using a network as it allows us to capture the richness of all relationships, to infer metrics such as the strength of connectivity or weaknesses in a supply chain, as well as derive new relationships due the nature and plasticity of the network topology itself.” commented Richard Freeman, PhD, co-founder and CTO of Architecture and Data Science at Vamstar.

How will we maximise the usefulness of the world’s largest healthcare supply chain network?

Any technology, no matter how advanced the AI or novel deep learning, needs to be applied with a clear ROI, leveraged for insights and make useful recommendations to the healthcare and life sciences industry, government bodies and society. At Vamstar, we are constantly speaking and engaging with suppliers, buyers, government, and investors, and in order to reinforce our reach and engagement we are working with a team of healthcare public procurement experts led by Dr Aris Georgopoulos from the University of Nottingham.

“Transparency has been one of the main characteristics of modern public procurement regulation and policy. However, transparency of information does not always lead to “visibility of information” as indicated by our research. This lack of visibility is even more prevalent in the connections between the various entities in the healthcare supply chain networks. Due to the scale of the relevant data and the complexity of relationships/connections, the challenge for increased visibility can only be solved using technological solutions, based on Artificial Intelligence (AI), Deep Learning, Natural Language Processing (NLP) and big data analysis which can function as efficiency multipliers assisting public buyers to achieve better and more sustainable outcomes.”  Dr Aris Georgopoulos, Assistant Professor in European and Public Law at the School of Law of the University of Nottingham and Co-Lead of the Research Unit on Public Procurement, Human Rights and Social Sustainability, of the Public Procurement Research Group (PPRG).

Vamstar is a data science powered global B2B healthcare and life sciences marketplace platform. They aggregate $2 trillion of demand for healthcare products and services using machine learning and providing real-time insights to buyers and suppliers to accelerate transactions.

Vamstar’s enriched data on buyers, outcomes, and contracts (including tenders) reveal interdependencies across complex contracting markets. By seeing the big picture and all the connections, Vamstar provides healthcare stakeholders with valuable market insights and perspectives.

Vamstar partners with leaders in the industry, academia, and government in 70 countries to apply higher-level thinking to daily tasks and strategic issues. They offer their customers solutions to make them more efficient and help them make data-driven informed decisions to secure their future. For more information, visit https://vamstar.io

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.

The University of Nottingham is a research-intensive university with a proud heritage, consistently ranked among the world’s top 100. Studying at the University of Nottingham is a life-changing experience and we pride ourselves on unlocking the potential of our students. We have a pioneering spirit, expressed in the vision of our founder Sir Jesse Boot, which has seen us lead the way in establishing campuses in China and Malaysia – part of a globally connected network of education, research and industrial engagement. We are ranked eighth for research power in the UK according to REF 2014. We have six beacons of research excellence helping to transform lives and change the world; we are also a major employer and industry partner – locally and globally. For more information, visit https://www.nottingham.ac.uk