Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.25954 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908619820236800 |
|---|---|
| author | Metz, Lynn Haggard, Rachel Moszczynski, Michael Asbah, Samer Mwase, Chris Khomani, Patricia Smith, Tyler Cooper, Hannah Mwale, Annie Muslim, Arbaaz Prasad, Gautam Sun, Mimi Shekel, Tomer Paul, Joydeep Carter, Anna Shetty, Shravya Green, Dylan |
| author_facet | Metz, Lynn Haggard, Rachel Moszczynski, Michael Asbah, Samer Mwase, Chris Khomani, Patricia Smith, Tyler Cooper, Hannah Mwale, Annie Muslim, Arbaaz Prasad, Gautam Sun, Mimi Shekel, Tomer Paul, Joydeep Carter, Anna Shetty, Shravya Green, Dylan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25954 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Application and Validation of Geospatial Foundation Model Data for the Prediction of Health Facility Programmatic Outputs -- A Case Study in Malawi Metz, Lynn Haggard, Rachel Moszczynski, Michael Asbah, Samer Mwase, Chris Khomani, Patricia Smith, Tyler Cooper, Hannah Mwale, Annie Muslim, Arbaaz Prasad, Gautam Sun, Mimi Shekel, Tomer Paul, Joydeep Carter, Anna Shetty, Shravya Green, Dylan Machine Learning Artificial Intelligence J.3 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. |
| title | Application and Validation of Geospatial Foundation Model Data for the Prediction of Health Facility Programmatic Outputs -- A Case Study in Malawi |
| topic | Machine Learning Artificial Intelligence J.3 |
| url | https://arxiv.org/abs/2510.25954 |