Early Alzheimer’s Disease Prediction Using Multimodal Longitudinal Data
Background:

Alzheimer’s Disease (AD) is a progressive and currently incurable neurodegenerative disorder. Early detection is critical for enabling timely interventions and improving patient outcomes. While previous research has primarily focused on predicting AD conversion in patients with Mild Cognitive Impairment (MCI) using baseline multimodal data, this thesis aims to go a step further by incorporating temporal patterns in longitudinal data.

Your tasks:

The goal of this thesis is to leverage longitudinal multimodal data including clinical and MRI measurements from the ADNI dataset to improve early prediction of AD. Specifically, the objectives are: (a) Predict the likelihood of conversion to AD within a 5-year window from a given prediction point. (b) Estimate the likely time of disease onset using up to 5 years of historical multimodal data.

What we offer:

You will receive guidance and essential resources to support your research, including:
 

  • Assistance with accessing and organizing the ADNI dataset, including longitudinal clinical and imaging data
  • Code for data processing and feature extraction
  • Basic multimodal fusion code to get started
  • Regular meetings to discuss progress and provide feedback on thesis writing
Project details:

Ideal Candidate Profile
 

  • Background in machine learning, medical imaging, biomedical engineering, or a related field
  • Experience with Python and deep learning frameworks (PyTorch)
  • Interest in medical applications of AI, particularly neurodegenerative disease prediction

Thesis Details
 

References:

Liu S, Zhang B, Zimmer V A, et al. Multi-modal Data Fusion with Missing Data Handling for Mild Cognitive Impairment Progression Prediction[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024: 293-302.

Liu S, Zhang B, Fang R, et al. Dynamic graph neural representation based multi-modal fusion model for cognitive outcome prediction in stroke cases[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2023: 338-347.