Advancing disease progression prediction by AI with multimodality data

In recent years, AI-based models have rapidly developed and achieved numerous successful applications in clinical practice. Some of the proposed tools have reached a level as real clinicians, where they can identify and predict various diseases, including diabetic retinopathy and skin cancer. However, the most successful algorithm is a simple classifier to tell if the disease is absent or not, but without considering its progression over time.

This project aims to transform disease prognosis and monitoring through cutting-edge AI techniques. By leveraging longitudinal and multimodal data—including various imaging modalities and textual clinical information—we aim to develop advanced models for tracking disease progression and improving patient care. This research represents a groundbreaking step toward more dynamic, interpretable, and effective AI tools in healthcare.

Project Objectives:

The core of this research focuses on creating spatial-temporal AI models to handle historical multimodal data, enabling better disease monitoring, treatment planning, and management. The project will address two critical challenges:

1.      Using Historical Data for Disease Progression Tracking:

Building upon existing AI diagnostic systems, which mainly classify the presence of a disease, this research will extend capabilities to predict disease development over time using historical patient data.

2.      Multimodal Data Integration for Enhanced Decision-Making:

Beyond imaging data, this project will incorporate multimodal information such as diagnostic reports and patient medical histories. By integrating clinical knowledge, the models aim to deliver comprehensive, accurate, and interpretable predictions to support informed decision-making.

Candidate requirements:

We invite applications from highly motivated and talented PhD candidates interested in developing state-of-the-art AI solutions for healthcare. Applicants must hold/achieve a minimum of a merit at master’s degree level (or international equivalent) in a science, mathematics or engineering discipline. Applicants without a master's qualification may be considered on an exceptional basis, provided they hold a first-class undergraduate degree. The English language requirements must also be met by the start of the PhD.

How to apply:

Please contact He Zhao (he.zhao@liverpool.ac.uk) to discuss prior to submitting an online application. Please insert [PhD_CSC_application], written backwards, in your email subject. Please strictly follow the instruction for easy access to your email.

Online

applications could follow the guidance on https://www.liverpool.ac.uk/study/fees-and-funding/scholarships-and-bursaries/postgraduate-researchers/other-scholarships-and-awards/china-scholarship-council-award/.