Application and Validation of Geospatial Foundation Model Data for the Prediction of Health Facility Programmatic Outputs -- A Case Study in Malawi

2025-10-29

AI Summary

To address pervasive reporting delays and incomplete coverage in routine health data from low- and middle-income countries (LMICs), this study proposes a novel predictive framework integrating heterogeneous geospatial data sources. We systematically evaluate, for the first time, the utility of population dynamics, high-resolution satellite imagery, and mobile phone signaling data for predicting primary healthcare outputs in LMICs. Leveraging multi-source embedding fusion, we develop Multi-GeoFM—a foundation model tailored to geospatial health forecasting—and integrate it with XGBoost under five-fold cross-validation to predict 15 key health indicators across 552 health catchment areas in Malawi. Results demonstrate superior performance over conventional geostatistical methods for 13 indicators; on test sets, R² reaches 0.64 for population density, 0.68 for new HIV cases, and 0.55 for childhood vaccination coverage. This framework establishes a scalable, methodological paradigm for real-time, fine-grained health monitoring in LMICs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The reliability of routine health data in low and middle-income countries (LMICs) is often constrained by reporting delays and incomplete coverage, necessitating the exploration of novel data sources and analytics. Geospatial Foundation Models (GeoFMs) offer a promising avenue by synthesizing diverse spatial, temporal, and behavioral data into mathematical embeddings that can be efficiently used for downstream prediction tasks. This study evaluated the predictive performance of three GeoFM embedding sources - Google Population Dynamics Foundation Model (PDFM), Google AlphaEarth (derived from satellite imagery), and mobile phone call detail records (CDR) - for modeling 15 routine health programmatic outputs in Malawi, and compared their utility to traditional geospatial interpolation methods. We used XGBoost models on data from 552 health catchment areas (January 2021-May 2023), assessing performance with R2, and using an 80/20 training and test data split with 5-fold cross-validation used in training. While predictive performance was mixed, the embedding-based approaches improved upon baseline geostatistical methods in 13 of 15 (87%) indicators tested. A Multi-GeoFM model integrating all three embedding sources produced the most robust predictions, achieving average 5-fold cross validated R2 values for indicators like population density (0.63), new HIV cases (0.57), and child vaccinations (0.47) and test set R2 of 0.64, 0.68, and 0.55, respectively. Prediction was poor for prediction targets with low primary data availability, such as TB and malnutrition cases. These results demonstrate that GeoFM embeddings imbue a modest predictive improvement for select health and demographic outcomes in an LMIC context. We conclude that the integration of multiple GeoFM sources is an efficient and valuable tool for supplementing and strengthening constrained routine health information systems.

Problem

• Predicting health outputs using geospatial foundation models
• Improving routine health data reliability in low-income countries
• Integrating multiple GeoFM sources for robust health predictions

Innovation

• Using GeoFM embeddings for health prediction tasks
• Integrating multiple GeoFM sources for robust predictions
• Applying XGBoost models on geospatial foundation data