Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GAMMA-PD: Graph-based Analysis of Multi-Modal Motor Impairment Assessments in Parkinson's Disease

Favour Nerrise, Alice Louise Heiman, Ehsan Adeli

TL;DR

The proposed GAMMA-PD (Graph-based Analysis of Multi-modal Motor Impairment Assessments in Parkinson's Disease), a novel heterogeneous hypergraph fusion framework for multi-modal clinical data analysis, integrates imaging and non-imaging data into a "hypernetwork" by preserving higher-order information and similarity between patient profiles and symptom subtypes.

Abstract

The rapid advancement of medical technology has led to an exponential increase in multi-modal medical data, including imaging, genomics, and electronic health records (EHRs). Graph neural networks (GNNs) have been widely used to represent this data due to their prominent performance in capturing pairwise relationships. However, the heterogeneity and complexity of multi-modal medical data still pose significant challenges for standard GNNs, which struggle with learning higher-order, non-pairwise relationships. This paper proposes GAMMA-PD (Graph-based Analysis of Multi-modal Motor Impairment Assessments in Parkinson's Disease), a novel heterogeneous hypergraph fusion framework for multi-modal clinical data analysis. GAMMA-PD integrates imaging and non-imaging data into a "hypernetwork" (patient population graph) by preserving higher-order information and similarity between patient profiles and symptom subtypes. We also design a feature-based attention-weighted mechanism to interpret feature-level contributions towards downstream decision tasks. We evaluate our approach with clinical data from the Parkinson's Progression Markers Initiative (PPMI) and a private dataset. We demonstrate gains in predicting motor impairment symptoms in Parkinson's disease. Our end-to-end framework also learns associations between subsets of patient characteristics to generate clinically relevant explanations for disease and symptom profiles. The source code is available at https://github.com/favour-nerrise/GAMMA-PD.

GAMMA-PD: Graph-based Analysis of Multi-Modal Motor Impairment Assessments in Parkinson's Disease

TL;DR

The proposed GAMMA-PD (Graph-based Analysis of Multi-modal Motor Impairment Assessments in Parkinson's Disease), a novel heterogeneous hypergraph fusion framework for multi-modal clinical data analysis, integrates imaging and non-imaging data into a "hypernetwork" by preserving higher-order information and similarity between patient profiles and symptom subtypes.

Abstract

The rapid advancement of medical technology has led to an exponential increase in multi-modal medical data, including imaging, genomics, and electronic health records (EHRs). Graph neural networks (GNNs) have been widely used to represent this data due to their prominent performance in capturing pairwise relationships. However, the heterogeneity and complexity of multi-modal medical data still pose significant challenges for standard GNNs, which struggle with learning higher-order, non-pairwise relationships. This paper proposes GAMMA-PD (Graph-based Analysis of Multi-modal Motor Impairment Assessments in Parkinson's Disease), a novel heterogeneous hypergraph fusion framework for multi-modal clinical data analysis. GAMMA-PD integrates imaging and non-imaging data into a "hypernetwork" (patient population graph) by preserving higher-order information and similarity between patient profiles and symptom subtypes. We also design a feature-based attention-weighted mechanism to interpret feature-level contributions towards downstream decision tasks. We evaluate our approach with clinical data from the Parkinson's Progression Markers Initiative (PPMI) and a private dataset. We demonstrate gains in predicting motor impairment symptoms in Parkinson's disease. Our end-to-end framework also learns associations between subsets of patient characteristics to generate clinically relevant explanations for disease and symptom profiles. The source code is available at https://github.com/favour-nerrise/GAMMA-PD.
Paper Structure (8 sections, 5 equations, 3 figures, 1 table)

This paper contains 8 sections, 5 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Heterogeneous Hypergraph Construction
  4. Hypergraph Convolution & Attention Learning
  5. Experiments
  6. Results & Discussion
  7. Clinical Interpretability
  8. Conclusion

Figures (3)

  • Figure 1: GAMMA-PD: (A) For each patient $i$, we pre-process their multi-modal medical record, which includes structured imaging data $m_i$ and unstructured non-imaging data $b_i$. We fuse both data into patient (node-level) features. We also cluster patient subgroups based on five similarity types from non-imaging data. (B) We form a population heterogeneous hypergraph containing all patients, their combined features, and relationships between them across different similarity types. This multiplex network is analyzed using neural networks to identify patterns within patient subgroups. (C) We classify the patients' gait impairment ratings (MDS-UPDRS 3.10), predict their TD/PIGD scores, and provide interpretable patient subtype profiles.
  • Figure 2: Top-10 thresholded ROI connections via attention-based brain networks for predicting PIGD score SensoriMotor Network, Salience Network, and Cerebellar Network.
  • Figure 3: Subtype profile of PD-PIGD predictions characterized by feature similarity activity within brain functional networks.