EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care

Juan F Gaitán-Guerrero, Carmen Martínez-Cruz, Macarena Espinilla, David Díaz-Jiménez, Jose L López

Computer Methods and Programs in Biomedicine · 2025-09 · 269 · 108878

DOI: 10.1016/j.cmpb.2025.108878 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2025-09. Verfasst von Juan F Gaitán-Guerrero und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Jaén, Jaén, 23071, Spain. Electronic address: jgaitan@ujaen.es. Hauptthemen laut MEDLINE: Diabetes Mellitus, Language. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Regional Development Fund, State Agency of Research, Ministerio de Ciencia, Innovación y Universidades.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: Diabetes is a global health concern, affecting millions of adults worldwide and exhibiting a growing prevalence. Managing the disease highly relies on continuous glucose monitoring, yet the dense and complex nature of electronic devices data streams poses significant challenges for efficient interpretation. Large Language Models are being widely applied across different domains for their ability to generate human-like text, but still fall short in producing accurate and meaningful text from raw data. To address this limitation, this study proposes a fine-tuning methodology tailored specifically to glucose data, but scalable to other expert-guided domains, enabling the models to generate concise, relevant and safe summaries, bridging the gap between raw data and efficient medical attention. METHODS: This study introduces a novel continuous glucose monitoring framework that involves fine-tuned GPT models using structured datasets generated through an expert-guided data modeling based on Fuzzy Logic and prompt engineering for task contextualization. A new evaluation methodology is defined to assess the performance of the Large Language Models across different critical domains where expert knowledge is fundamental to characterize temporally dependent data and ensure valuable insights. RESULTS: Fine-tuned GPT-4o achieved the highest performance, with an average score of 96% across all metrics. GPT-4o-mini followed with 76% score, while GPT-3.5 scored 72%. The use of fuzzy knowledge-based prompts proved more effective in scenarios with full data availability, or in scenarios with a simplified data availability when the models are not fine-tuned; domain-guided prompts improved output relevance and stability in fine-tuned models with less data availability. CONCLUSIONS: These results indicate the capability of our methods to align Large Language Models with the task of generating human-like text from raw data, highlighting their potential to manage diabetes by complex glucose patterns interpretation, alleviating the burden on healthcare systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetes MellitusLanguageHumansFuzzy LogicBlood GlucoseBlood Glucose Self-MonitoringAlgorithmsLarge Language Models

Stichwörter der Autor:innen

Continuous glucose monitoringEvaluation methodologyFine-tuning processIoT-data fuzzy summarizationLarge language modelsPrompt engineering

Substanzen

Blood Glucose

Autor:innen und Institutionen

  • Department of Computer Science, University of Jaén, Jaén, 23071, Spain. Electronic address: jgaitan@ujaen.es.
  • Department of Languages and Computer Systems, University of Granada, E.T.S. de Ingenierías Informática y de Telecomunicación, Granada, 18071, Spain. Electronic address: cmcruz@ugr.es.
  • Department of Computer Science, University of Jaén, Jaén, 23071, Spain. Electronic address: mestevez@ujaen.es.
  • Department of Computer Science, University of Jaén, Jaén, 23071, Spain. Electronic address: ddjimene@ujaen.es.
  • Department of Computer Science, University of Jaén, Jaén, 23071, Spain. Electronic address: llopez@ujaen.es.

Förderung

  • European Regional Development Fund
  • State Agency of Research
  • Ministerio de Ciencia, Innovación y Universidades
  • Universidad de Jaén

Zitieren

APA

Gaitán-Guerrero, J. F., Martínez-Cruz, C., Espinilla, M., Díaz-Jiménez, D., & López, J. L. (2025). A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care. Computer Methods and Programs in Biomedicine, 269, 108878. https://doi.org/10.1016/j.cmpb.2025.108878

Vancouver

Gaitán-Guerrero JF, Martínez-Cruz C, Espinilla M, Díaz-Jiménez D, López JL. A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care. Computer Methods and Programs in Biomedicine. 2025;269:108878. doi:10.1016/j.cmpb.2025.108878

BibTeX
@article{GaitnGuerrero2025,
  author = {Gaitán-Guerrero, Juan F and Martínez-Cruz, Carmen and Espinilla, Macarena and Díaz-Jiménez, David and López, Jose L},
  title = {A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2025},
  volume = {269},
  pages = {108878},
  doi = {10.1016/j.cmpb.2025.108878}
}
Kostenlos starten →