Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study
JMIR Medical Informatics · 08.09.2025 · 13 · e76252
DOI: 10.2196/76252 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 08.09.2025. Verfasst von Chen Pan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hepatobiliary and Vascular Surgery, First Affiliated Hospital of Chengdu Medical College, Chengdu, China. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Liver Neoplasms. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Primary liver cancer, particularly hepatocellular carcinoma (HCC), poses significant clinical challenges due to late-stage diagnosis, tumor heterogeneity, and rapidly evolving therapeutic strategies. While systematic reviews and meta-analyses are essential for updating clinical guidelines, their labor-intensive nature limits timely evidence synthesis.
Objective
This study proposes an automated literature screening workflow powered by large language models (LLMs) to accelerate evidence synthesis for HCC treatment guidelines.
Methods
We developed a tripartite LLM framework integrating Doubao-1.5-pro-32k, Deepseek-v3, and DeepSeek-R1-Distill-Qwen-7B to simulate collaborative decision-making for study inclusion and exclusion. The system was evaluated across 9 reconstructed datasets derived from published HCC meta-analyses, with performance assessed using accuracy, agreement metrics (κ and prevalence-adjusted bias-adjusted κ), recall, precision, F1-scores, and computational efficiency parameters (processing time and cost).
Results
The framework demonstrated good performance, with a weighted accuracy of 0.96 and substantial agreement (prevalence-adjusted bias-adjusted κ=0.91), achieving high weighted recall (0.90) but modest weighted precision (0.15) and F1-scores (0.22). Computational efficiency varied across datasets (processing time: 248-5850 s; cost: US $0.14-$3.68 per dataset).
Conclusions
This LLM-driven approach shows promise for accelerating evidence synthesis in HCC care by reducing screening time while maintaining methodological rigor. Key limitations related to clinical context sensitivity and error propagation highlight the need for reinforcement learning integration and domain-specific fine-tuning. LLM agent architectures with reinforcement learning offer a practical path for streamlining guideline updates, though further optimization is needed to improve specialization and reliability in complex clinical settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Hepatobiliary and Vascular Surgery, First Affiliated Hospital of Chengdu Medical College, Chengdu, China.
ORCID-Profile: Chen Pan, Wei Lu, Bingliang Chen, Gang Zhang, Zhiming Yang, Jingcheng Hao
Zitieren
APA
Pan, C., Lu, W., Chen, B., Zhang, G., Yang, Z., & Hao, J. (2025). Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study. JMIR Medical Informatics, 13, e76252. https://doi.org/10.2196/76252
Vancouver
Pan C, Lu W, Chen B, Zhang G, Yang Z, Hao J. Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study. JMIR Medical Informatics. 2025;13:e76252. doi:10.2196/76252
BibTeX
@article{Pan2025,
author = {Pan, Chen and Lu, Wei and Chen, Bingliang and Zhang, Gang and Yang, Zhiming and Hao, Jingcheng},
title = {Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study},
journal = {JMIR Medical Informatics},
year = {2025},
volume = {13},
pages = {e76252},
doi = {10.2196/76252}
}
EUVIMED