Jingpeng Li

Jingpeng Li

Auto-generated profile, based on publicly available information

Jingpeng Li

State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 November 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
DWDingqiao Wang
Dingqiao Wang
JLJiangbo Liang
Jiangbo Liang
JYJinguo Ye
Jinguo Ye
JLJingni Li
Jingni Li
JLJingpeng Li
Jingpeng Li
YZYingfeng Zheng
Yingfeng Zheng
Background: Large language models (LLMs) demonstrated advanced performance in processing clinical information. However, commercially available LLMs lack specialized medical knowledge and remain susceptible to generating inaccurate information. Given the need for self-management in diabetes, patients commonly seek information online. We introduce the Retrieval-augmented Information System for Enhancement (RISE) framework and evaluate its performance in enhancing LLMs to provide accurate responses to diabetes-related inquiries. Objective: This study aimed to evaluate the potential of the RISE framework, an information retrieval and augmentation tool, to improve the LLM’s performance to accurately and safely respond to diabetes-related inquiries. Methods: The RISE, an innovative retrieval augmentation framework, comprises 4 steps: rewriting query, information retrieval, summarization, and execution. Using a set of 43 common diabetes-related questions, we evaluated 3 base LLMs (GPT-4, Anthropic Claude 2, Google Bard) and their RISE-enhanced versions respectively. Assessments were conducted by clinicians for accuracy and comprehensiveness and by patients for understandability. Results: The integration of RISE significantly improved the accuracy and comprehensiveness of responses from all 3 base LLMs. On average, the percentage of accurate responses increased by 12% (15/129) with RISE. Specifically, the rates of accurate responses increased by 7% (3/43) for GPT-4, 19% (8/43) for Claude 2, and 9% (4/43) for Google Bard. The framework also enhanced response comprehensiveness, with mean scores improving by 0.44 (SD 0.10). Understandability was also enhanced by 0.19 (SD 0.13) on average. Data collection was conducted from September 30, 2023 to February 5, 2024. Conclusions: The RISE significantly improves LLMs’ performance in responding to diabetes-related inquiries, enhancing accuracy, comprehensiveness, and understandability. These improvements have crucial implications for RISE’s future role in patient education and chronic illness self-management, which contributes to relieving medical resource pressures and raising public awareness of medical knowledge.

15 August 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
TZTian Zhou
Tian Zhou
ZYZiqi Yang
Ziqi Yang
HZHong Zhou
Hong Zhou
BNBiyan Ni
Biyan Ni
YZYang Zhou
Yang Zhou
CHChang He
Chang He
Microglia are central regulators of retinal immune homeostasis, yet their pathogenic states in retinal degeneration remain less well understood. Here we identified a distinct subset of lipid-accumulated reactive microglia (aLARM), using scRNA sequencing and spatial transcriptomics in NaIO3-induced retinal degeneration mice, predominantly localized to the outer retina. aLARM were conserved across mouse models and patients and uniquely marked by high CD36 expression. Microglia-specific CD36 deletion abolished aLARM-mediated inflammation and degeneration, whereas subretinal transplantation of CD36+ aLARM exacerbated retinal structural destruction and functional impairment. Mechanistically, CD36+ aLARM activated NLRP3 inflammasome and produced IL-1β, engaging IL-1R1 on microglia/macrophages and pericytes/SMCs to amplify a feed-forward inflammatory circuit. Therapeutic CD36 blockade with the neutralizing antibody FA6-152 reduced aLARM formation and protected against neurodegeneration. Together, our findings highlight CD36+ aLARM as a targetable pathogenic microglial population linking neuroinflammation to retinal degeneration, providing a potential foundation for microglia-based precision therapies.

4 March 2024 in JMIR Preprints
Verified
Preprint
Open access
DWDingqiao Wang
Dingqiao Wang
JLJiangbo Liang
Jiangbo Liang
JYJinguo Ye
Jinguo Ye
JLJingni Li
Jingni Li
JLJingpeng Li
Jingpeng Li
YZYingfeng Zheng
Yingfeng Zheng
BACKGROUND Large language models (LLMs) demonstrated advanced performance in processing clinical information. However, commercially available LLMs lack specialized medical knowledge and remain susceptible to generating inaccurate information. Given the need for self-management in diabetes, patients commonly seek information online. We introduce the Retrieval-augmented Information System for Enhancement (RISE) framework and evaluate its performance in enhancing LLMs to provide accurate responses to diabetes-related inquiries. OBJECTIVE This study aimed to evaluate the potential of the RISE framework, an information retrieval and augmentation tool, to improve the LLM’s performance to accurately and safely respond to diabetes-related inquiries. METHODS The RISE, an innovative retrieval augmentation framework, comprises 4 steps: rewriting query, information retrieval, summarization, and execution. Using a set of 43 common diabetes-related questions, we evaluated 3 base LLMs (GPT-4, Anthropic Claude 2, Google Bard) and their RISE-enhanced versions respectively. Assessments were conducted by clinicians for accuracy and comprehensiveness and by patients for understandability. RESULTS The integration of RISE significantly improved the accuracy and comprehensiveness of responses from all 3 base LLMs. On average, the percentage of accurate responses increased by 12% (15/129) with RISE. Specifically, the rates of accurate responses increased by 7% (3/43) for GPT-4, 19% (8/43) for Claude 2, and 9% (4/43) for Google Bard. The framework also enhanced response comprehensiveness, with mean scores improving by 0.44 (SD 0.10). Understandability was also enhanced by 0.19 (SD 0.13) on average. Data collection was conducted from September 30, 2023 to February 5, 2024. CONCLUSIONS The RISE significantly improves LLMs’ performance in responding to diabetes-related inquiries, enhancing accuracy, comprehensiveness, and understandability. These improvements have crucial implications for RISE’s future role in patient education and chronic illness self-management, which contributes to relieving medical resource pressures and raising public awareness of medical knowledge.