Lulu Cui

Supervisors: Professor Cagatay Turkay and Professor Frances Griffiths

Research interests: Adaptive Visualization, Explainable AI (XAI) in Healthcare; Multimodal Transport and Healthcare Access

Background

I completed my Master of Interaction Design and Electronic Arts at the University of Sydney, following my Bachelor's degree in Design Computing from the same university. I also participated in an exchange program at Zhejiang University. In 2022, I worked as an Information Engineering Experiencer at Huawei.

Research

PhD working title: Adaptive Visualization for Addressing Transport-Related Health Inequities in UK

Research Topic: Lulu’s project develops an explainable and adaptive visualization framework to address inequalities in healthcare access stemming from transport barriers within UK. Building on established spatial accessibility modelling techniques, the research uses machine learning to identify complex relationships between transport networks, population demographics, and healthcare utilization patterns. However, unlike traditional "black box" approaches, this project emphasizes XAI, ensuring that the underlying logic of the models is transparent and interpretable to end-users. The resulting interactive visual analytics dynamically reconfigure to present data from the most relevant perspectives for diverse stakeholders, including public health officers, transport planners, and community representatives. By enabling users to jointly explore complex spatial data, such as the impact of public transport schedules and service reliability on access to specific healthcare facilities. The project aims to foster shared understanding, build trust in data-driven insights, and ultimately create a collaborative decision-support tool that identifies and communicates optimal, equitable interventions for improving healthcare access across UK.

Research Aim: The primary aim of this research is to develop and evaluate a novel, data-driven framework using XAI and adaptive visualization to address transport-related inequities in healthcare access within UK. This framework will integrate multimodal transport data, healthcare utilization records, and machine learning models to quantify the impact of transport systems on access. Crucially, it will translate complex model outputs into actionable knowledge through interactive visualizations tailored to diverse stakeholders, promoting shared understanding and collaborative decision-making. The goal is to inform evidence-based policies and interventions that optimize transport infrastructure, improve healthcare service delivery, and foster a more equitable healthcare landscape within the country.

Grants

• Chancellor’s International Scholarship 2025/2026