EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Utilizing RAG and GPT-4 for Extraction of Substance Use Information from Clinical Notes

Fatemeh Shah-Mohammadi, Joseph Finkelstein

Studies in Health Technology and Informatics · 2024

DOI: 10.3233/shti241070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2024. Verfasst von Fatemeh Shah-Mohammadi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, School of Medicine, University of Utah, USA. Hauptthemen laut MEDLINE: Substance-Related Disorders, Natural Language Processing. Die Arbeit wurde bisher 9-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research investigates the application of a hybrid Retrieval-Augmented Generation (RAG) and Generative Pre-trained Transformer (GPT) pipeline for extracting and categorizing substance use information from unstructured clinical notes. The aim is to enhance the accuracy and efficiency of identifying substance use mentions and determining their status in patient documentation. By integrating RAG to pre-filter and focus the input for GPT, the pipeline strategically narrows the scope of analysis to the most relevant text segments, thereby improving the precision and recall of the extraction. Utilizing the Medical Information Mart for Intensive Care III dataset, the performance of the pipeline was evaluated through manual verification, assessing various metrics including recall, precision, F1-score, and accuracy. The results demonstrated high precision rates (up to 0.99 for drug and alcohol mentions), and substantial recall (0.88 across all substances for status of the usage).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Substance-Related DisordersNatural Language ProcessingHumansElectronic Health RecordsData MiningInformation Storage and Retrieval

Stichwörter der Autor:innen

GPTRetrieval-augmented generation (RAG)Substance use information

Autor:innen und Institutionen

  • Department of Biomedical Informatics, School of Medicine, University of Utah, USA.

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Shah-Mohammadi, F., & Finkelstein, J. (2024). Utilizing RAG and GPT-4 for Extraction of Substance Use Information from Clinical Notes. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti241070

Vancouver

Shah-Mohammadi F, Finkelstein J. Utilizing RAG and GPT-4 for Extraction of Substance Use Information from Clinical Notes. Studies in Health Technology and Informatics. 2024. doi:10.3233/shti241070

BibTeX
@article{ShahMohammadi2024,
  author = {Shah-Mohammadi, Fatemeh and Finkelstein, Joseph},
  title = {Utilizing RAG and GPT-4 for Extraction of Substance Use Information from Clinical Notes},
  journal = {Studies in Health Technology and Informatics},
  year = {2024},
  doi = {10.3233/shti241070}
}
Kostenlos starten →