EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Address Normalization Framework Using Fine-Tuned LLMs to Enhance Geospatial Intelligence in Cancer Registries

Ricardo Timarán Pereira, Jonathan Viveros Córdoba, Arsenio Hidalgo Troya, Luisa Bravo Goyes, Anívar Chaves Torres, Fredy Vidal Alegría, Andres Oswaldo Calderon Romero, Ginna Leyton Yela

Electronics · 20.07.2026 · 15 (14) · 3176

DOI: 10.3390/electronics15143176 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 20.07.2026. Verfasst von Ricardo Timarán Pereira und 7 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Technology and Innovation MINCIENCIAS, Universidad de Nariño, Open and Distance University UNAD.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Population-based Cancer Registry of the Municipality of Pasto (RPCMP) faces significant challenges in spatial data integrity due to the high variability, inconsistency, and ambiguity of manually collected addresses. Such limitations restrict the analytical capacity of the YACHAY-GIS platform to generate precise geospatial intelligence across multiscalar levels. To address these issues, this paper proposes a novel hybrid address normalization framework structured in two sequential stages. First, a specialized deterministic geocoding engine, optimized for local urban morphology, is utilized. Second, for highly non-standard records—characterized by “block and lot” (manzana y lote) nomenclatures—a workflow based on Large Language Models (LLMs) is integrated. To ensure computational efficiency in resource-constrained environments, a Supervised Fine-Tuning (SFT) process was implemented using the Low-Rank Adaptation (LoRA) technique across various open-source LLMs. Experimental results demonstrate that the workflow integrated with the Llama-3.2-3B-Instruct model achieved the highest performance, with a normalization accuracy of 99.40%. The end-to-end evaluation shows an increase in spatial recovery from a 33.02% baseline to 55.13%, effectively isolating the semantic gap from the underlying cartographic limitations of the region. This architecture provides a scalable data engineering model for oncological registries, with future work focused on integrating external spatial providers such as OpenStreetMap and Colombia’s Agustín Codazzi Geographic Institute (IGAC) to further enhance geographic coverage.

Förderung

  • Ministry of Science, Technology and Innovation MINCIENCIAS
  • Universidad de Nariño
  • Open and Distance University UNAD
  • University Institution Colegio Mayor del Cauca

Zitieren

APA

Pereira, R. T., Córdoba, J. V., Troya, A. H., Goyes, L. B., Torres, A. C., Alegría, F. V., Romero, A. O. C., & Yela, G. L. (2026). A Hybrid Address Normalization Framework Using Fine-Tuned LLMs to Enhance Geospatial Intelligence in Cancer Registries. Electronics, 15(14), 3176. https://doi.org/10.3390/electronics15143176

Vancouver

Pereira RT, Córdoba JV, Troya AH, Goyes LB, Torres AC, Alegría FV, et al. A Hybrid Address Normalization Framework Using Fine-Tuned LLMs to Enhance Geospatial Intelligence in Cancer Registries. Electronics. 2026;15(14):3176. doi:10.3390/electronics15143176

BibTeX
@article{Pereira2026,
  author = {Pereira, Ricardo Timarán and Córdoba, Jonathan Viveros and Troya, Arsenio Hidalgo and Goyes, Luisa Bravo and Torres, Anívar Chaves and Alegría, Fredy Vidal and Romero, Andres Oswaldo Calderon and Yela, Ginna Leyton},
  title = {A Hybrid Address Normalization Framework Using Fine-Tuned LLMs to Enhance Geospatial Intelligence in Cancer Registries},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {14},
  pages = {3176},
  doi = {10.3390/electronics15143176}
}
Kostenlos starten →