SRShumin Ren

Shumin Ren

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shumin Ren has a total of 27 co-authors. Here are the top co-authors by number of shared publications:

  • Bairong Shen

    Department of Respiratory and Critical Care Medicine and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu, China

    5 shared publications
  • Rongrong Wu

    Joint Laboratory of Artificial Intelligence for Critical Care Medicine, Department of Critical Care Medicine and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu, China

    4 shared publications
  • Xingyun Liu

    Affiliations Health Management Center, General Practice Medical Center and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu, China, Department of Computer Science and Information Technology, University of A Coruña, Coruña, Spain

    4 shared publications
  • Li Shen

    Department of Integrated Traditional Chinese and Western Medicine The Fourth Affiliated Hospital of Soochow University (Suzhou Dushu Lake Hospital) Suzhou Jiangsu China

    3 shared publications
  • Bingqing Liu

    2 shared publications
  • Cheng Bi

    Department of Ophthalmology and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West China Hospital of Sichuan University, No.2222, Xinchuan Road, Gaoxin District, Chengdu, Sichuan, 610041, China, 86 15995854635

    2 shared publications

Latest Publications

  • Open Access

    Knowledge-Guided Explainable Recommendation Tool for Cancer Risk Prediction Models Using Retrieval-Augmented Large Language Models: Development and Validation Study

    by Shumin Ren, Xin Zheng, Jing Zhao, Jiale Du, Yuxin Zhang, Cheng Bi, Jie Song, Jinyi Zhang, Hongmei Lang, Fan Zhang, et al.

    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 <.05). It also demonstrated high authenticity, data completeness, and consistency. Baseline applications frequently returned incomplete, inconsistent, or fabricated results, especially for complex, multifactorial queries, whereas CanRisk-RAG delivered accurate and structured recommendations grounded in validated evidence. Conclusions: CanRisk-RAG presents a transparent, domain-specific, and semantically enriched framework for discovering cancer risk prediction models, addressing several limitations of existing keyword-based search tools and general-purpose LLMs. By integrating structured knowledge, multifactor ranking, and LLM-based reasoning, the system aims to improve the precision, reproducibility, and usability of model selection in cancer risk prediction. While our evaluation demonstrates encouraging performance compared with baseline systems, further validation in broader clinical contexts and real-world applications is warranted. The framework’s general design may also be adaptable to other clinical model domains, providing a potential foundation for advancing evidence-based model discovery in precision medicine.


  • Open Access

    PEP-DSS-DBC1.0: A Personalized Exercise Prescription Decision Support System for Diabetes Care (Preprint)

    by Ting Bao, Xingyun Liu, Shumin Ren, Ke Zhang, Jiale Du, Danting Li, Bingqing Liu, Jinhua Feng, Rongrong Wu, Erman Wu, et al.

    BACKGROUND Exercise plays a critical role in managing diabetes, improving glycemic control, and reducing the risk of cardiovascular complications. However, personalizing exercise prescriptions (PEPs) to address individual characteristics and preferences is challenging, particularly in an environment with a global shortage of exercise professionals. While digital tools hold promise for improving personalized care, many existing systems rely on generalized guidelines or expert consensus, lacking the ability to provide highly individualized and evidence-based recommendations. To address this gap, we developed PEP-DSS-DBC1.0, a knowledge-based digital decision support system for generating tailored PEPs in diabetes care. OBJECTIVE The aim of this study was to create a digital, knowledge-based decision support tool for personalized exercise prescriptions that incorporates individual characteristics and preferences. PEP-DSS-DBC1.0 was designed to enhance the precision and usability of PEPs for people with diabetes while ensuring alignment with evidence-based principles. METHODS The development of PEP-DSS-DBC1.0 was informed by an extensive review of the literature. A working group, including experts in exercise medicine, diabetes care, and informatics, was formed to establish a decision support framework. The PubMed database served as the primary resource for knowledge extraction, covering studies published between January 1975 and May 2023. Data from 938 studies were annotated, resulting in 1,171 exercise protocols, 10,316,497 patient records, and 2,904 additional entries, totaling 13,263 data points. The web-based tool was built using a browser/server architecture and the WIMA (Windows, IIS, MySQL, ASP.NET) web stack. Validation and comparative analysis of the tool were performed against ChatGPT4o and sports physicians, using multiple metrics and two rating scales: the System Usability Scale (SUS) and the Net Promoter Score (NPS). RESULTS PEP-DSS-DBC1.0 provides personalized exercise prescriptions based on the newly developed “FITT-VP-WC” principles, which include frequency, intensity, time, type, volume, progression, warning, and contraindication. The tool demonstrated superior performance compared to ChatGPT4o and sports physicians, achieving a total performance score of 100% compared to 48% for ChatGPT4o and 12% for sports physicians (χ2=853.3, P<.001). Usability assessments showed that the average SUS score was 77.25 ± 6.06, indicating above-average usability, while the NPS score was 68.75%, reflecting high user loyalty and satisfaction. The tool is freely accessible at http://PEP-DSS-DBC.sysbio.org.cn/. CONCLUSIONS PEP-DSS-DBC1.0 represents a significant advancement in diabetes care, providing a knowledge-based system for generating highly individualized exercise prescriptions. While the tool has demonstrated superior performance and usability, future randomized controlled trials are essential to further validate its clinical utility and broader application in diabetes management.

  • Prevention of exercise-related injuries and adverse events in patients with diabetes:a scoping review

    by Ting Bao, Bingqing Liu, Danting Li, Jiale Du, Jinhua Feng, Xingyun Liu, Rongrong Wu, Shumin Ren, Erman Wu, Wei Gao, et al.

    INPLASY2023110047 Prevention of exercise-related injuries and adverse events in patients with diabetes:a scoping review Keywords: Diabetes; scoping review; exercise; physical activity; adverse even…

  • Open Access

    CTRR-ncRNA: A Knowledgebase for Cancer Therapy Resistance and Recurrence Associated Non-Coding RNAs

    by Tong Tang, Xingyun Liu, Rongrong Wu, Li Shen, Shumin Ren, Bairong Shen

    Cancer therapy resistance and recurrence (CTRR) are the dominant causes of death in cancer patients. Recent studies have indicated that non-coding RNAs (ncRNAs) can not only reverse the resistance to cancer therapy but also are crucial biomarkers for the evaluation and prediction of CTRR. Herein, we developed CTRR-ncRNA, a knowledgebase of CTRR-associated ncRNAs, aiming to provide an accurate and comprehensive resource for research involving the association between CTRR and ncRNAs. Compared to most of the existing cancer databases, CTRR-ncRNA is focused on the clinical characterization of cancers, including cancer subtypes, as well as survival outcomes and responses to personalized therapy of cancer patients. Information pertaining to biomarker ncRNAs has also been documented for the development of personalized CTRR prediction. A user-friendly interface and several functional modules have been incorporated into the database. Based on the preliminary analysis of genotype–phenotype relationships, universal ncRNAs have been found to be potential biomarkers for CTRR. The CTRR-ncRNA is a translation-oriented knowledgebase and it provides a valuable resource for mechanistic investigations and explainable artificial intelligence-based modeling. CTRR-ncRNA is freely available to the public at http://ctrr.bioinf.org.cn/.


  • Open Access

    CTRR-ncRNA: A Translation-oriented Knowledgebase for Cancer Resistance and Recurrence Associated Non-coding RNAs

    by Tong Tang, Xingyun Liu, Rongrong Wu, Li Shen, Shumin Ren, Bairong Shen

    Cancer therapy resistance and recurrence (CTRR) are the dominant causes of death in cancer patients. Recent studies have indicated that non-coding RNAs (ncRNAs) can not only reverse the resistance to cancer therapy but also are crucial biomarkers for the evaluation and prediction of CTRR. Herein, we developed CTRR-ncRNA, a knowledgebase of CTRR-associated ncRNAs, aiming to provide an accurate and comprehensive resource for research involving association between CTRR and ncRNAs. Compared to most of the existing cancer databases, CTRR-ncRNA is focused on the clinical characterization of cancers, including cancer subtypes, as well as survival outcomes and response to personalized therapy of cancer patients. Information pertaining to biomarker ncRNAs has also been documented for the development of personalized CTRR prediction. A user-friendly interface and several functional modules have been incorporated into the database. Based on the preliminary analysis of genotype–phenotype relationships, universal ncRNAs have been found to be potential biomarkers for CTRR. The CTRR-ncRNA is a translation-oriented knowledgebase and it provides a valuable resource for mechanistic investigations and explainable artificial intelligence-based modelling. CTRR-ncRNA is freely available to the public at http://ctrr.bioinf.org.cn/ .