During the first wave of COVID-19, I watched patients fighting one infection fall victim to another - one we didn’t see coming.

It wasn’t from outside. It was spreading within the hospital (Read the BBC Story).

At the time, I was volunteering in hospitals and working with Imperial College Healthcare NHS Trust to deliver real-time forecasts of bed and ventilator demand. I had just begun a PhD in Mathematics at Imperial College London, building predictive models to track the spread of antimicrobial resistance.

But what I saw inside hospitals made something painfully clear: we weren’t just fighting a virus - we were flying blind when it came to how infections were spreading between patients.

That’s when the question struck me: what if we could see infections coming -before they spread?

Each year, drug-resistant bacteria cause 136 million infections¹ and are estimated to contribute to as many as 39 million deaths over the next 25 years². These aren’t distant threats - they’re happening in our hospitals, in the middle of routine care. Even outside of pandemics, around 10% of hospital patients acquire an infection during their stay³. And most hospitals lack systems to track- or reliably predict - how these infections spread.

I had seen these threats up close - first in my earlier work in biodefense and infection detection, and now again, during the COVID crisis. The risks were not just biological, but structural: data was scattered, staff were overwhelmed, and decisions had to be made reactively, often too late.

That’s when the idea for NEX was born: a system that could make infection control proactive, not just reactive. One that could utilise existing data within hospitals to detect diseases early, identify who’s at risk, and forecast where transmission might occur next.

Around that time, I met Dr. Chang Ho Yoon, an infectious diseases physician from the University of Oxford. We were both working at the Alan Turing Institute and quickly found a shared frustration with the static nature of infection control systems - and a shared vision for how AI and real-time data could help hospitals act earlier, with greater clarity and precision.

We started by building tools to help infection control teams visualise where infections were - and where they were likely to go. Then we developed predictive analytics grounded in clinical and epidemiological evidence. Our models were validated across hundreds of thousands of patient records from major hospital systems in the UK and Asia.

In 2023, we published a landmark study in The Lancet Digital Health (Read the paper), demonstrating that hospital-onset infections can be anticipated days in advance - offering a critical window for prevention.

That work became the foundation of NEX. List more in our podcast:

20 JULY 2022

19 MIN

THE LANCET DIGITAL HEALTH

Ashleigh Myall on predicting hospital-onset COVID-19 infections

Ashleigh Myall joins Diana Samuel to discuss a new machine-learning framework that integrates dynamic patient-contact networks with patient clinical variables and contextual hospital variables to predict hospital-onset COVID-19 infections.

Listen to Podcast

Today, the NEX platform is being deployed in hospitals across the UK and Southeast Asia. It helps infection prevention and control teams see not just what’s happening, but what’s about to happen - supporting faster, more targeted, and more effective responses to outbreaks and transmission risks.

Because the future of infection control isn’t just about reacting to the past.

It’s about predicting what’s next - and stopping preventable infections before they start.