EUVIMEDEUVIMED entdecken
Crossref

An Entity Extraction pipeline for Medical Text Records Utilizing Large Language Models: An Analytical Study (Preprint)

Lei Wang, Yuanliang Ma, Wenya Linda Bi, Hong Yan Lv, Yuxiang Li

Greater South Information System · 15.11.2023

DOI: 10.60692/vg4n4-p0262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Greater South Information System, erschienen am 15.11.2023. Verfasst von Lei Wang und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study of disease progression relies on clinical data, including text data, and extracting valuable features from text data has been a research hot spot. With the rise of large language models (LLMs), semantic-based extraction pipelines are gaining acceptance in clinical research. However, the security and feature hallucination issues of LLMs require further attention.This study aimed to introduce a novel modular LLM pipeline, which could semantically extract features from textual patient admission records.The pipeline was designed to process a systematic succession of concept extraction, aggregation, question generation, corpus extraction, and question-and-answer scale extraction, which was tested via 2 low-parameter LLMs: Qwen-14B-Chat (QWEN) and Baichuan2-13B-Chat (BAICHUAN). A data set of 25,709 pregnancy cases from the People's Hospital of Guangxi Zhuang Autonomous Region, China, was used for evaluation with the help of a local expert's annotation. The pipeline was evaluated with the metrics of accuracy and precision, null ratio, and time consumption. Additionally, we evaluated its performance via a quantified version of Qwen-14B-Chat on a consumer-grade GPU.The pipeline demonstrates a high level of precision in feature extraction, as evidenced by the accuracy and precision results of Qwen-14B-Chat (95.52% and 92.93%, respectively) and Baichuan2-13B-Chat (95.86% and 90.08%, respectively). Furthermore, the pipeline exhibited low null ratios and variable time consumption. The INT4-quantified version of QWEN delivered an enhanced performance with 97.28% accuracy and a 0% null ratio.The pipeline exhibited consistent performance across different LLMs and efficiently extracted clinical features from textual data. It also showed reliable performance on consumer-grade hardware. This approach offers a viable and effective solution for mining clinical research data from textual records.

Schlagwörter

named entity recognitionlarge language modelsclinical text miningconcept extractionquestion generationhallucinationsINT4 quantizationdisease progression

Zitieren

APA

Wang, L., Ma, Y., Bi, W. L., Lv, H. Y., & Li, Y. (2023). An Entity Extraction pipeline for Medical Text Records Utilizing Large Language Models: An Analytical Study (Preprint). Greater South Information System. https://doi.org/10.60692/vg4n4-p0262

Vancouver

Wang L, Ma Y, Bi WL, Lv HY, Li Y. An Entity Extraction pipeline for Medical Text Records Utilizing Large Language Models: An Analytical Study (Preprint). Greater South Information System. 2023. doi:10.60692/vg4n4-p0262

BibTeX
@article{Wang2023,
  author = {Wang, Lei and Ma, Yuanliang and Bi, Wenya Linda and Lv, Hong Yan and Li, Yuxiang},
  title = {An Entity Extraction pipeline for Medical Text Records Utilizing Large Language Models: An Analytical Study (Preprint)},
  journal = {Greater South Information System},
  year = {2023},
  doi = {10.60692/vg4n4-p0262}
}
Kostenlos starten →