Knowledge-Guided Explainable Recommendation Tool for Cancer Risk Prediction Models Using Retrieval-Augmented Large Language Models: Development and Validation Study
JMIR Medical Informatics · 2026
DOI: 10.2196/78519 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift JMIR Medical Informatics, 2026. Verfasst von Shumin Ren und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institutes for Systems Genetics, West China Hospital of Sichuan University, Frontiers Science Center for Disease-related Molecular Network, Chengdu, …. Hauptthemen laut MEDLINE: Neoplasms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Cancer risk prediction models are vital for precision prevention, enabling individualized assessment of cancer susceptibility based on genetic, clinical, environmental, and lifestyle factors. However, the practical use of these models is hindered by fragmented resources, heterogeneous reporting, and the absence of transparent, structured systems for systematic discovery and comparison.
Objective
This study aimed to develop a retrieval-augmented, knowledge-guided system that provides accurate recommendations for cancer risk prediction models.
Methods
We developed CanRisk-RAG, a recommendation platform underpinned by a precisely constructed knowledge base comprising more than 800 peer-reviewed cancer risk prediction models spanning diverse cancer types, modeling approaches, and predictive variables. The system integrates (1) large language model (LLM)–based semantic tag extraction, (2) embedding vectorization of structured metadata and abstracts, (3) a multifactor ranking algorithm combining semantic similarity with multiple quality indicators, and (4) LLM-generated literature summarization to support rapid user interpretation. Performance was evaluated across 4 types of representative queries. Eight domain experts independently assessed retrieval quality. CanRisk-RAG was benchmarked against PubMed, ChatGPT-4o, ScholarAI, and Gemini 1.5 Flash.
Results
On the independent validation set, CanRisk-RAG consistently outperformed all 4 baseline applications, achieving the highest overall relevance (8.30 [SD 0.59]) and reliability (7.62 [SD 0.76]) scores on a 10-point scale ( P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institutes for Systems Genetics, West China Hospital of Sichuan University, Frontiers Science Center for Disease-related Molecular Network, Chengdu, Sichuan, 610041, China, 86 15995854635.
- West China School of Medicine, Sichuan University, Sichuan University affiliated Chengdu Second People's Hospital, Chengdu Second People's Hospital, Chengdu, Sichuan, China.
- Health Management Center, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
ORCID-Profile: Shumin Ren, Xin Zheng, Jing Zhao, Jiale Du, Yuxin Zhang, Cheng Bi, Jie Song, Jinyi Zhang, Hongmei Lang, Fan Zhang, Bairong Shen
Zitieren
APA
Ren, S., Zheng, X., Zhao, J., Du, J., Zhang, Y., Bi, C., Song, J., Zhang, J., Lang, H., Zhang, F., & Shen, B. (2026). Knowledge-Guided Explainable Recommendation Tool for Cancer Risk Prediction Models Using Retrieval-Augmented Large Language Models: Development and Validation Study. JMIR Medical Informatics. https://doi.org/10.2196/78519
Vancouver
Ren S, Zheng X, Zhao J, Du J, Zhang Y, Bi C, et al. Knowledge-Guided Explainable Recommendation Tool for Cancer Risk Prediction Models Using Retrieval-Augmented Large Language Models: Development and Validation Study. JMIR Medical Informatics. 2026. doi:10.2196/78519
BibTeX
@article{Ren2026,
author = {Ren, Shumin and Zheng, Xin and Zhao, Jing and Du, Jiale and Zhang, Yuxin and Bi, Cheng and Song, Jie and Zhang, Jinyi and Lang, Hongmei and Zhang, Fan and Shen, Bairong},
title = {Knowledge-Guided Explainable Recommendation Tool for Cancer Risk Prediction Models Using Retrieval-Augmented Large Language Models: Development and Validation Study},
journal = {JMIR Medical Informatics},
year = {2026},
doi = {10.2196/78519}
}
EUVIMED