Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI.

Journal: NeuroImage
PMID: 38942101

Abstract

BACKGROUND: The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI).

Authors

  • Fernando García-Gutiérrez
    Department of Neurology, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad Complutense, Madrid, Spain.
  • Laura Hernández-Lorenzo
    Department of Neurology, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad Complutense, Madrid, Spain.
  • María Nieves Cabrera-Martín
    Department of Nuclear Medicine, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad Complutense, Madrid, Spain.
  • Jordi A Matias-Guiu
    Department of Neurology, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad Complutense, Madrid, Spain.
  • José L Ayala
    Department of Computer Architecture and Automation, Universidad Complutense, Madrid, Spain.

Keywords

External Resources

Popular Topics
Recent Journals