PHGNN: A Novel Prompted Hypergraph Neural Network to Diagnose Alzheimer's Disease
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913744455467008 |
|---|---|
| author | Liu, Chenyu Rossi, Luca |
| author_facet | Liu, Chenyu Rossi, Luca |
| contents | The accurate diagnosis of Alzheimer's disease (AD) and prognosis of mild cognitive impairment (MCI) conversion are crucial for early intervention. However, existing multimodal methods face several challenges, from the heterogeneity of input data, to underexplored modality interactions, missing data due to patient dropouts, and limited data caused by the time-consuming and costly data collection process. In this paper, we propose a novel Prompted Hypergraph Neural Network (PHGNN) framework that addresses these limitations by integrating hypergraph based learning with prompt learning. Hypergraphs capture higher-order relationships between different modalities, while our prompt learning approach for hypergraphs, adapted from NLP, enables efficient training with limited data. Our model is validated through extensive experiments on the ADNI dataset, outperforming SOTA methods in both AD diagnosis and the prediction of MCI conversion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14577 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PHGNN: A Novel Prompted Hypergraph Neural Network to Diagnose Alzheimer's Disease Liu, Chenyu Rossi, Luca Machine Learning Artificial Intelligence The accurate diagnosis of Alzheimer's disease (AD) and prognosis of mild cognitive impairment (MCI) conversion are crucial for early intervention. However, existing multimodal methods face several challenges, from the heterogeneity of input data, to underexplored modality interactions, missing data due to patient dropouts, and limited data caused by the time-consuming and costly data collection process. In this paper, we propose a novel Prompted Hypergraph Neural Network (PHGNN) framework that addresses these limitations by integrating hypergraph based learning with prompt learning. Hypergraphs capture higher-order relationships between different modalities, while our prompt learning approach for hypergraphs, adapted from NLP, enables efficient training with limited data. Our model is validated through extensive experiments on the ADNI dataset, outperforming SOTA methods in both AD diagnosis and the prediction of MCI conversion. |
| title | PHGNN: A Novel Prompted Hypergraph Neural Network to Diagnose Alzheimer's Disease |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.14577 |