Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study
JMIR Medical Informatics · 2025-09-08 · 13 · e76252
DOI: 10.2196/76252 ↗At a glance
Journal article in JMIR Medical Informatics, published online on 2025-09-08. Written by Chen Pan and 5 co-authors. Institution: Department of Hepatobiliary and Vascular Surgery, First Affiliated Hospital of Chengdu Medical College, Chengdu, China. Major MEDLINE topics: Carcinoma, Hepatocellular, Liver Neoplasms. Cited 8 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.
Abstract (original language)
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.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Hepatobiliary and Vascular Surgery, First Affiliated Hospital of Chengdu Medical College, Chengdu, China.
ORCID profiles: Chen Pan, Wei Lu, Bingliang Chen, Gang Zhang, Zhiming Yang, Jingcheng Hao
Cite
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