EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Extracting Pediatric Information from Summaries of Product Characterics with a Large Language Model and No-Code

Elkaouther Zaoui, Cédric Bousquet, Catherine Duclos

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Elkaouther Zaoui und 2 weiteren Autor:innen. Beteiligte Einrichtung: Université Sorbonne Paris Nord, Laboratoire d'Informatique Médicale et d'Ingénierie des connaissances en e-Santé, LIMICS, Sorbonne Université, INSERM…. Hauptthemen laut MEDLINE: Natural Language Processing, Data Mining, Pediatrics, Information Storage and Retrieval. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate medication information is important for children, as dosing errors can have severe consequences compared to adults. We propose an automated method to extract pediatric information from Summaries of Product Characteristics (SPC). We used AirOps, a commercial and no-code visual editor to implement a processing chain with large language model GPT-4o mini on 50 SPCs. The task focused on evaluating pediatric indications and we extracted relevant sentences from all segments with a 95% recall rate and 78% precision rate. The results suggest the model can reliably classify drugs according to their pediatric indications. A no-code approach made it possible to implement the task for a healthcare professional with no training in information technology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingData MiningPediatricsInformation Storage and RetrievalElectronic Health RecordsHumansChildMedication ErrorsLarge Language Models

Stichwörter der Autor:innen

Artificial IntelligenceChildDrug informationLarge Language ModelNLPSPCUser-Computer Interface

Autor:innen und Institutionen

  • Université Sorbonne Paris Nord, Laboratoire d'Informatique Médicale et d'Ingénierie des connaissances en e-Santé, LIMICS, Sorbonne Université, INSERM, F-93000, Bobigny, France.

Zitieren

APA

Zaoui, E., Bousquet, C., & Duclos, C. (2025). Extracting Pediatric Information from Summaries of Product Characterics with a Large Language Model and No-Code. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250651

Vancouver

Zaoui E, Bousquet C, Duclos C. Extracting Pediatric Information from Summaries of Product Characterics with a Large Language Model and No-Code. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250651

BibTeX
@article{Zaoui2025,
  author = {Zaoui, Elkaouther and Bousquet, Cédric and Duclos, Catherine},
  title = {Extracting Pediatric Information from Summaries of Product Characterics with a Large Language Model and No-Code},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250651}
}
Kostenlos starten →