IET - Going viral: Harnessing Deep Learning and Quantum Materials for Early Disease Diagnosis

14th March 2024 5:00 pm

The silent pandemic of antimicrobial resistance ranks among the top ten global health threats facing humanity, and could kill 10 million people annually by 2050, at a cost to the global economy of $100 trillion.

There is growing recognition of the critical role of diagnostics in guiding patient management and antibiotic usage, yet the development of fit-for-purpose tests for antimicrobial resistance and models for decentralised diagnostic delivery, remains a major challenge.

Gold-standard laboratory tests, such as culture or PCR, while highly accurate, typically require posting samples to centralised labs and waiting for test results, resulting in diagnosis delays and inappropriate prescribing. Low-cost lateral flow tests which give results within minutes, have come to the fore during the COVID-19 pandemic by widening access to testing in decentralised community settings (e.g. pharmacies, GPs, care homes, schools and at home).

However, lateral flow tests typically lack sensitivity to early infections, resulting in false negatives. Hence there is an urgent need for high-performance rapid tests to accurately diagnose early-stage infections and antimicrobial resistance in community settings.

Herein, with IET A F Harvey Engineering Research Prize funding, I seek to exploit my team’s recent breakthroughs in quantum nanodiamond diagnostics and deep learning of rapid tests to revolutionise the early diagnosis of antimicrobial resistance, focusing on drug resistant Tuberculosis as an exemplar.

If successful, this ground-breaking early-stage research could lay the foundations of next-stage translational funding and open-up applications to other communicable and non-communicable diseases.

Listed in Other Institutions' Events

Cite Top