Yujie Dai

Project title: Explainable AI for UTI Diagnosis and Antibiotic Resistance Prediction

Supervisory team: Professor Andrew Dowsey (primary), Professor Raul Santos Rodriguez (secondary), Professor Brian Sullivan

Project summary:

Urinary Tract Infections (UTIs) are common and can significantly affect patients’ quality of life, yet accurate diagnosis remains difficult due to overlapping symptoms and delayed lab results. These challenges often lead to inappropriate antibiotic use, contributing to growing antibiotic resistance.

Using a linked Electronic Health Record (EHR) dataset from primary care, hospitals, and pathology labs, this project applies Explainable AI to identify key predictors of UTI risk and antibiotic resistance. The goal is to support faster, more accurate diagnosis and promote responsible antibiotic prescribing through transparent and interpretable AI models.

General Profile:

I graduated from the Beijing Institute of Technology with a BSc in Software Engineering in 2020 and then worked there for a year as a research assistant. During this time, I developed a interest in artificial intelligence and machine learning, particularly in their potential to improve healthcare and enhance quality of life.

In 2022, I completed an MSc in Artificial Intelligence with Distinction at the University of St Andrews. My dissertation investigated how the structure of human contact networks influences the spread of infectious diseases.

As a PhD candidate in the Digital Health and Care CDT programme, my current research focuses on developing explainable AI models to enhance diagnostic accuracy and address challenges in infectious diseases, with a particular focus on antibiotic resistance. By working with large-scale Electronic Health Records (EHRs), I aim to extract insights that can support clinicians and improve patient outcomes