MedGNN: Capturing the Links Between Urban Characteristics and Medical Prescriptions

• URL: http://arxiv.org/abs/2504.04739v1
• Date: Mon, 07 Apr 2025 05:35:16 GMT
• Title: MedGNN: Capturing the Links Between Urban Characteristics and Medical Prescriptions
• Authors: Minwei Zhao, Sanja Scepanovic, Stephen Law, Daniele Quercia, Ivica Obadic,
• Abstract summary: We propose MedGNN, a graph neural network that integrates positional and locational node embeddings with urban characteristics in a graph neural network.<n>MedGNN improved predictions by over 25% on average compared to baseline methods.<n>These results demonstrate MedGNN's potential, and more broadly, of carefully applied machine learning to advance transdisciplinary public health research.
• Score: 2.5415925266871184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding how urban socio-demographic and environmental factors relate with health is essential for public health and urban planning. However, traditional statistical methods struggle with nonlinear effects, while machine learning models often fail to capture geographical (nearby areas being more similar) and topological (unequal connectivity between places) effects in an interpretable way. To address this, we propose MedGNN, a spatio-topologically explicit framework that constructs a 2-hop spatial graph, integrating positional and locational node embeddings with urban characteristics in a graph neural network. Applied to MEDSAT, a comprehensive dataset covering over 150 environmental and socio-demographic factors and six prescription outcomes (depression, anxiety, diabetes, hypertension, asthma, and opioids) across 4,835 Greater London neighborhoods, MedGNN improved predictions by over 25% on average compared to baseline methods. Using depression prescriptions as a case study, we analyzed graph embeddings via geographical principal component analysis, identifying findings that: align with prior research (e.g., higher antidepressant prescriptions among older and White populations), contribute to ongoing debates (e.g., greenery linked to higher and NO2 to lower prescriptions), and warrant further study (e.g., canopy evaporation correlated with fewer prescriptions). These results demonstrate MedGNN's potential, and more broadly, of carefully applied machine learning, to advance transdisciplinary public health research.

Related papers

• CureGraph: Contrastive Multi-Modal Graph Representation Learning for Urban Living Circle Health Profiling and Prediction [13.681538916025021]
  We propose CureGraph, a contrastive multi-modal representation learning framework for urban health prediction.<n>CureGraph infers the prevalence of common chronic diseases among the elderly within the urban living circles of each neighborhood.<n>It captures cross-modal spatial dependencies, offering a comprehensive understanding of urban environments tailored to elderly health considerations.
  arXiv  Detail & Related papers  (2025-01-13T09:30:38Z)
• How Your Location Relates to Health: Variable Importance and Interpretable Machine Learning for Environmental and Sociodemographic Data [15.463748602675695]
  Health outcomes depend on complex environmental and sociodemographic factors whose effects change over location and time.<n>We use fine-grained spatial and temporal data to study these effects, namely the MEDSAT dataset of English health, environmental, and sociodemographic information.<n>We then develop an interpretable machine learning framework based on Generalized Additive Models (GAMs) and Multiscale Geographically Weighted Regression (MGWR)<n>Our findings identify NO2 as a global predictor for asthma, hypertension, and anxiety, alongside other outcome-specific predictors related to occupation, marriage, and vegetation.
  arXiv  Detail & Related papers  (2025-01-03T21:34:35Z)
• Integrating Social Determinants of Health into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare [47.23120247002356]
  Social determinants of health (SDoH) play a crucial role in patient health outcomes, yet their integration into biomedical knowledge graphs remains underexplored.<n>This study addresses this gap by constructing an SDoH-enriched knowledge graph using the MIMIC-III dataset and PrimeKG.
  arXiv  Detail & Related papers  (2024-11-29T20:35:01Z)
• Epidemiology-informed Graph Neural Network for Heterogeneity-aware Epidemic Forecasting [46.63739322178277]
  Recent studies have demonstrated the strong potential of of-temporal neural networks (STGNNs) in extracting heterogeneous-temporal epidemic patterns. HeatGNN learns epidemiology-informed locations embedding different locations that reflect their own transmission mechanisms over time. HeatGNN outperforms various strong baselines of HeatHeat on different sizes of Heat.
  arXiv  Detail & Related papers  (2024-11-26T12:29:45Z)
• A Comparative Study of Population-Graph Construction Methods and Graph Neural Networks for Brain Age Regression [48.97251676778599]
  In medical imaging, population graphs have demonstrated promising results, mostly for classification tasks. extracting population graphs is a non-trivial task and can significantly impact the performance of Graph Neural Networks (GNNs) In this work, we highlight the importance of a meaningful graph construction and experiment with different population-graph construction methods.
  arXiv  Detail & Related papers  (2023-09-26T10:30:45Z)
• Fact-Checking Generative AI: Ontology-Driven Biological Graphs for Disease-Gene Link Verification [45.65374554914359]
  We aim to achieve fact-checking of the knowledge embedded in biological graphs that were contrived from ChatGPT contents. We adopted a biological networks approach that enables the systematic interrogation of ChatGPT's linked entities. This study demonstrated high accuracy of aggregate disease-gene links relationships found in ChatGPT-generated texts.
  arXiv  Detail & Related papers  (2023-08-07T22:13:30Z)
• Multimodal brain age estimation using interpretable adaptive population-graph learning [58.99653132076496]
  We propose a framework that learns a population graph structure optimized for the downstream task. An attention mechanism assigns weights to a set of imaging and non-imaging features. By visualizing the attention weights that were the most important for the graph construction, we increase the interpretability of the graph.
  arXiv  Detail & Related papers  (2023-07-10T15:35:31Z)
• Decoding Urban-health Nexus: Interpretable Machine Learning Illuminates Cancer Prevalence based on Intertwined City Features [1.4010916616909745]
  Age, minority status, and population density are among the most influential factors in cancer prevalence. Increasing green space and reducing developed areas and total emissions could alleviate cancer prevalence.
  arXiv  Detail & Related papers  (2023-06-20T18:56:37Z)
• Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications [52.65389473899139]
  Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Recent works have shown that considering relationships between input data samples have a positive regularizing effect for the downstream task. We propose Graph-in-Graph (GiG), a neural network architecture for protein classification and brain imaging applications.
  arXiv  Detail & Related papers  (2022-04-01T10:01:37Z)
• IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction [47.999621481852266]
  We propose an interpretable graph learning-based model which interprets the clinical relevance of the input features towards the task. In a clinical scenario, such a model can assist the clinical experts in better decision-making for diagnosis and treatment planning. Our proposed model shows superior performance with respect to compared methods with an increase in an average accuracy of 3.2% for Tadpole, 1.6% for UKBB Gender, and 2% for the UKBB Age prediction task.
  arXiv  Detail & Related papers  (2021-03-29T13:04:02Z)
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks [2.9488233765621295]
  We present a higher-order graph convolutional network (HOGCN) to aggregate information from the higher-order neighborhood for biomedical interaction prediction. Experiments on four interaction networks, including protein-protein, drug-drug, drug-target, and gene-disease interactions, show that HOGCN achieves more accurate and calibrated predictions.
  arXiv  Detail & Related papers  (2020-10-16T17:16:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.