UKRI Centre for Doctoral Training in Safe and Trusted AI (STAI CDT) aligned PhD student, Stephen Asiedu, was part of an award winning team in a two-day Hackathon. It was hosted at Imperial College London and organised by I-X Business Partner, Fetch.ai Innovation Lab.
The hackathon challenge, provided by Moderna, an Imperial Business Partner, focused on addressing vaccine hesitancy by mapping patient journeys. Participants analysed data from sources like social media and surveys to identify key milestones in overcoming hesitancy and create solutions using Fetch.ai uAgents technology to deliver personalized, impactful engagement strategies.
Final projects were presented to an expert panel, which was made up of:
- Phillip Cruz, Country Medical Director at Moderna (Chair)
- Satwik Kar, National Medical Science Liaison at Moderna
- Kshipra Dhame Developer Advocate at Fetch.ai
- Abhi Gangani, Developer Advocate at Fetch.ai
Hack VHS
Stephen was part of a team of multidisciplinary Imperial students, which included Emma Pajak (Department of Chemical Engineering), Tristan Spreng (Department of Chemical Engineering), Arushi Sinha (Department of Earth Science and Engineering), and Piotr Toka (Department of Chemistry).
Their team, Hack VHS, was awarded a prize by the panel for, ‘Best use of Fetch.ai Tech’ and came 3rd overall.
Stephen explains how Hack VHS works below:
“We created HackVHS, an AI-powered tool designed to combat vaccine hesitancy through a combination of data analysis, user profiling, and personalised engagement. It starts by analysing real-world data, such as vaccine-related Twitter posts, to identify common reasons for hesitancy. This data is displayed on an interactive dashboard where users can explore the findings and fill out a survey. Based on their survey responses, users are classified into three categories of persuasion: logic (logos), emotion (pathos), or peer-pressure/authority (ethos).
A Retrieval-Augmented Generation (RAG) agent powered by a Vectara LLM and trained on World Health Organisation (WHO) data then provides tailored responses. For instance, users classified as logic-driven will see data-heavy graphs and statistics, while emotion-driven users will receive anecdotal stories, and authority-driven users will encounter endorsements from trusted experts. As users interact with the system, a patient journey agent tracks and analyses their responses, visualising their journey and highlighting key touchpoints where their opinions shifted. Medical Affairs teams can access these insights to refine public outreach strategies and better address vaccine hesitancy in the future.”
Being Part of the Hackathon
Stephen really enjoyed being part of the hackathon and shared that, “It was an exhilarating experience, combining the thrill of competition with the chance to tackle a meaningful global challenge. It provided a unique opportunity to collaborate with talented individuals and leverage cutting-edge tools like Fetch.ai and Vectara LLM. We were inspired by the shared purpose of creating a solution that could make a real-world impact.”
The multidisciplinary approach of the team was a particular highlight for Stephen and it was rewarding to see all their work come together – integrating AI, real-world data analysis, and user profiling – into a cohesive prototype. He said, “The ability to address such a nuanced issue, like vaccine hesitancy, in such a short timeframe of 48 hours was both challenging and incredibly fulfilling.”
A huge congratulations to Stephen and team Hack VHS for your award and for taking part in such an exciting and innovative event. You can find more details about their project here: HackVHS | Devpost