Yanzeng Li

Yanzeng Li

Auto-generated profile, based on publicly available information

Yanzeng Li

Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
19 January 2026 in Nature Medicine
Verified
Journal Article
Open access
PDF file
XTXinge Tao
Xinge Tao
SZShuya Zhou
Shuya Zhou
KDKai Ding
Kai Ding
SLSairan Li
Sairan Li
YLYanzeng Li
Yanzeng Li
SHShasha Han
Shasha Han
Patient-facing large language models (LLMs) hold potential to streamline inefficient transitions from primary to specialist care. We developed the preassessment (PreA), an LLM chatbot co-designed with local stakeholders, to perform the general medical consultations for history-taking, preliminary diagnoses, and test ordering that would normally be performed by primary care providers and to generate referral reports for specialists. PreA was tested in a randomized controlled trial involving 111 specialists from 24 medical disciplines across two health centers, where 2,069 patients (1,141 women; 928 men) were randomly assigned to use PreA independently (PreA-only), use it with staff support (PreA-human), or not use it (No-PreA) before specialist consultation. The trial met its primary end points with the PreA-only group showing significantly reduced physician consultation duration (28.7% reduction; 3.14 ± 2.25 min) compared to the No-PreA group (4.41 ± 2.77 min; P < 0.001), alongside significant improvements in physician-perceived care coordination (mean scores 113.1% increase; 3.69 ± 0.90 versus 1.73 ± 0.95; P < 0.001) and patient-reported communication ease (mean scores 16.0% increase; 3.99 ± 0.62 versus 3.44 ± 0.97; P < 0.001). Equivalent outcomes between the PreA-only and PreA-human groups confirmed the autonomous operation capability. Co-designed PreA outperformed the same model with additional fine-tuning on local dialogues across clinical decision-making domains. Co-design with local stakeholders, compared to passive local data collecting, represents a more effective strategy for deploying LLMs to strengthen health systems and enhance patient-centered care in resource-limited settings. Chinese Clinical Trial Registry identifier: ChiCTR2400094159 .

1 January 2020
Verified
Conference Paper
Open access
PDF file
YLYanzeng Li
Yanzeng Li
BYBowen Yu
Bowen Yu
XMXue Mengge
Xue Mengge
TLTingwen Liu
Tingwen Liu
Yanzeng Li, Bowen Yu, Xue Mengge, Tingwen Liu. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

19 January 2026 in Nature Health
Verified
Journal Article
Open access
PDF file
SLSairan Li
Sairan Li
YLYanzeng Li
Yanzeng Li
SZShuya Zhou
Shuya Zhou
XTXinge Tao
Xinge Tao
CYChangjie Yu
Changjie Yu
SHShasha Han
Shasha Han
With a global shortage of primary healthcare physicians—particularly in resource-limited settings—large language models (LLMs) have the potential to support and enhance patients’ health awareness. Here we developed P&P Care (Population Medicine and Public Health), an LLM-powered primary care chatbot using a dual-track role-play codesign framework where community stakeholders and researchers simulated each another’s perspectives across four phases: contextual understanding; cocreation; testing and refinement; and implementation and evolution. The codesigned chatbot was integrated with e-learning modules and tested in a randomized controlled trial. The trial included 2,113 participants (1,052 women and 1,061 men) from urban and rural areas across 11 Chinese provinces who were randomly assigned to receive a consultation either with preparatory e-learning via the P&P Care or without. The study met its primary endpoint with the e-learning group showing significantly higher objective health awareness (mean score 2.95 ± 1.22) compared with the consultation-only group (mean score 2.34 ± 1.02; P < 0.001). Codesign offers a scalable solution for deploying LLMs in resource-limited settings. Chinese Clinical Trial Registry identifier: ChiCTR2500098101 .

1 January 2021
Verified
Conference Paper
Open access
PDF file
YLYanzeng Li
Yanzeng Li
BYBowen Yu
Bowen Yu
LQLi Quangang
Li Quangang
TLTingwen Liu
Tingwen Liu
Yanzeng Li, Bowen Yu, Li Quangang, Tingwen Liu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations. 2021.

19 February 2022 in Environmental Technology
Verified
Journal Article
Closed access
YPYanyan Peng
Yanyan Peng
ZCZhou Chen
Zhou Chen
YLYanzeng Li
Yanzeng Li
YWYuantao Wang
Yuantao Wang
CYChengsong Ye
Chengsong Ye
SZShenghua Zhang
Shenghua Zhang
Ozone is widely used to inactivate bacteria, fungi, and viruses. In recent years, the treatment of itchy skin diseases (eczema and atopic dermatitis) using trace ozone has also received attention. However, the feasibility of using trace ozone to replace personal care products (PCPs) has rarely been analyzed. In this study, the applicability of trace ozone was evaluated in terms of its efficiency for microbial inactivation in three types of skin microbiomes, cleaning performance on simulated human hair and epidermis, safety for simulated human hair, and contribution to emission reduction. The results revealed that at a 10:1 ratio of ozonated water to bacterial suspension, the inactivation ratios of Malassezia, C. albicans, and S. epidermidis reached 99.63%, 83.47%, and 100%, respectively. In addition, the cleaning performance of an ozone solution (0.4 mg/L) for simulated human skin contaminated with carbon black and sebum could reach 95.89% and 95.63%, respectively, with 5 min of washing. The average scores were 0.40 and 0.37 after 5 min and 10 min of ozone treatments, respectively, indicating that trace ozone does not significantly damage simulated human hair. Results also revealed that the total emissions of COD, TP, and TN would be reduced by 1.29×106, 3.55×103, and 3.63×103 mg/ (household · year), respectively, if PCPs are replaced by trace ozone. In short, our findings indicate that trace ozone is a potential alternative to PCPs. By replacing PCPs with trace ozone, the use of synthetic chemical products can be reduced and carbon emissions from oil extraction can be countered. GRAPHICAL ABSTRACT

21 October 2023
Verified
Conference Paper
Open access
YLYanzeng Li
Yanzeng Li
SHSen Hu
Sen Hu
WHWenjuan Han
Wenjuan Han
LZLei Zou
Lei Zou
As a fundamental subtask of Knowledge Base Question Answering (KBQA), Relation Detection (KBQA-RD) plays a crucial role to detect the KB relations between entities or variables in natural language questions. It remains, however, a challenging task, particularly for significant large-scale relations and in the presence of easily confused relations. Recent state-of-the-art methods not only struggle with such scenarios, but often take into account only one facet and fail to incorporate the subtle discrepancy among the relations. In this paper, we propose a simple and efficient three-stage framework to exploit the coarse-to-fine paradigm. Specifically, we employ a natural clustering over all KB relations and perform a coarse-to-fine relation recognition process based on the relation clustering. In this way, our framework (i.e., CORD) refines the detection of relations, so as to scale well with large-scale relations. Experiments on both single-relation (i.e., SimpleQuestions (SQ)) and multi-relation (i.e., WebQSP (WQ)) benchmarks show that CORD not only achieves the outstanding relation detection performance in KBQA-RD subtask; but more importantly, further improves the accuracy of KBQA systems.