Clustering Alzheimer's Disease Subtypes via Similarity Learning and Graph Diffusion

TL;DR

This paper presents a novel unsupervised clustering method using similarity learning and graph diffusion to identify five distinct Alzheimer's disease subtypes with different clinical and genetic features from MRI data.

Contribution

It introduces a new application of SIMLR and graph diffusion for AD subtyping, demonstrating improved clustering performance and revealing subtype-specific biomarkers and genetics.

Findings

Identified five distinct AD subtypes with unique clinical features.

Graph diffusion effectively reduces noise in MRI-based clustering.

Genetic analysis links subtypes to potential genetic underpinnings.

Abstract

Alzheimer's disease (AD) is a complex neurodegenerative disorder that affects millions of people worldwide. Due to the heterogeneous nature of AD, its diagnosis and treatment pose critical challenges. Consequently, there is a growing research interest in identifying homogeneous AD subtypes that can assist in addressing these challenges in recent years. In this study, we aim to identify subtypes of AD that represent distinctive clinical features and underlying pathology by utilizing unsupervised clustering with graph diffusion and similarity learning. We adopted SIMLR, a multi-kernel similarity learning framework, and graph diffusion to perform clustering on a group of 829 patients with AD and mild cognitive impairment (MCI, a prodromal stage of AD) based on their cortical thickness measurements extracted from magnetic resonance imaging (MRI) scans. Although the clustering approach we utilized has not been explored for the task of AD subtyping before, it demonstrated significantly better performance than several commonly used clustering methods. Specifically, we showed the power of graph diffusion in reducing the effects of noise in the subtype detection. Our results revealed five subtypes that differed remarkably in their biomarkers, cognitive status, and some other clinical features. To evaluate the resultant subtypes further, a genetic association study was carried out and successfully identified potential genetic underpinnings of different AD subtypes. Our source code is available at: https://github.com/PennShenLab/AD-SIMLR.