EUVIMEDEUVIMED entdecken
Crossref

Clinical insight from mesh implant narratives using zero-shot Retrieval-Augmented Generation approach

Indu Bala, Ekta Sharma, Lewis Mitchell

Artificial Intelligence Surgery · 16.10.2025 · 5 (4) · 476-88

DOI: 10.20517/ais.2025.44 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence Surgery, online erschienen am 16.10.2025. Verfasst von Indu Bala und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

Mesh implant surgeries for hernia repair are frequently associated with adverse events that can compromise patient outcomes. Extracting structured clinical insights from large-scale, unstructured data sources - such as the U.S. Food and Drug Administration’s Manufacturer and User Facility Device Experience (FDA MAUDE) database - remains a significant challenge due to the variability and subjectivity in patient-generated narratives.

Methods

This study evaluates the use of zero-shot prompting with a generative artificial intelligence (AI) model, both independently and in combination with a Retrieval-Augmented Generation (RAG) approach, to automate the extraction of structured summaries and adverse events from mesh-related FDA reports. The LLaMA 2 (13B) model was used to generate structured summaries (e.g., report date, hernia type, adverse event flag) and identify adverse events.

Results

The model outputs were compared to a manually annotated Benchmark Baseline. With zero-shot prompting alone, the model achieved accuracies of 67% for report date, 60% for hernia type, and 83% for adverse event flag. After integrating the RAG approach, these accuracies improved to 81%, 82%, and 99%, respectively. The accuracy for adverse event extraction increased from 60% to 86%, and the Jaccard similarity improved from 75% to 88.9%. Chi-square tests confirmed statistical significance (P < 0.05) for most of the observed improvements.

Conclusion

This study demonstrates that combining zero-shot generative AI with retrieval augmentation can effectively convert unstructured patient reports into structured data. This approach offers a scalable and interpretable method for adverse event monitoring in mesh implant surgeries and supports data-driven evaluation of patient-reported outcomes.

Zitieren

APA

Bala, I., Sharma, E., & Mitchell, L. (2025). Clinical insight from mesh implant narratives using zero-shot Retrieval-Augmented Generation approach. Artificial Intelligence Surgery, 5(4), 476-88. https://doi.org/10.20517/ais.2025.44

Vancouver

Bala I, Sharma E, Mitchell L. Clinical insight from mesh implant narratives using zero-shot Retrieval-Augmented Generation approach. Artificial Intelligence Surgery. 2025;5(4):476-88. doi:10.20517/ais.2025.44

BibTeX
@article{Bala2025,
  author = {Bala, Indu and Sharma, Ekta and Mitchell, Lewis},
  title = {Clinical insight from mesh implant narratives using zero-shot Retrieval-Augmented Generation approach},
  journal = {Artificial Intelligence Surgery},
  year = {2025},
  volume = {5},
  number = {4},
  pages = {476--88},
  doi = {10.20517/ais.2025.44}
}
Kostenlos starten →