Leveraging Geolocation in Clinical Records to Improve Alzheimer's Disease Diagnosis Using DMV Framework

2025-02-06

AI Summary

This study addresses the underrepresentation of environmental factors in early Alzheimer’s disease (AD) risk prediction by proposing DMV, the first framework integrating fine-grained geographic information with clinical text. Methodologically, it leverages Llama3-70B and GPT-4o to generate semantic embeddings from clinical notes and fuses them with high-resolution geospatial data—including residential coordinates and neighborhood-level environmental features—to jointly model linguistic and environmental exposures via regression. Its key contribution lies in the systematic incorporation of granular spatial variables into clinical natural language processing pipelines—a departure from conventional approaches relying solely on textual or structured clinical variables. Experimental results demonstrate that DMV reduces mean absolute error in continuous AD risk score prediction by 28.57% (with Llama3-70B) and 33.47% (with GPT-4o) over baseline models, quantitatively confirming the substantial added value of geographic context for enhancing early AD detection accuracy.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Alzheimer's Disease (AD) early detection is critical for enabling timely intervention and improving patient outcomes. This paper presents a DMV framework using Llama3-70B and GPT-4o as embedding models to analyze clinical notes and predict a continuous risk score associated with early AD onset. Framing the task as a regression problem, we model the relationship between linguistic features in clinical notes (inputs) and a target variable (data value) that answers specific questions related to AD risk within certain topic categories. By leveraging a multi-faceted feature set that includes geolocation data, we capture additional environmental context potentially linked to AD. Our results demonstrate that the integration of the geolocation information significantly decreases the error of predicting early AD risk scores over prior models by 28.57% (Llama3-70B) and 33.47% (GPT4-o). Our findings suggest that this combined approach can enhance the predictive accuracy of AD risk assessment, supporting early diagnosis and intervention in clinical settings. Additionally, the framework's ability to incorporate geolocation data provides a more comprehensive risk assessment model that could help healthcare providers better understand and address environmental factors contributing to AD development.

Problem

• Improving Alzheimer's Disease early detection
• Using geolocation data in clinical records
• Enhancing predictive accuracy with DMV framework

Innovation

• DMV framework with Llama3-70B
• GPT-4o for clinical note analysis
• Geolocation enhances AD risk prediction