Zhaoxi Fang

Dr. Zhaoxi Fang


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
30 May 2025 in Frontiers in Bioengineering and Biotechnology
Verified
Journal Article
Open access
PDF file
YWYaqing Wang
Yaqing Wang
HRHuajiang Ruan
Huajiang Ruan
YRYaoqin Ruan
Yaoqin Ruan
QLQi Li
Qi Li
CWChen Wang
Chen Wang
ZFZhaoxi Fang
Zhaoxi Fang
Blood collection is one of the key steps in blood testing. The use of intelligent blood collection robots to achieve automated blood collection can effectively reduce the workload of medical staff, improve the efficiency and accuracy of blood collection, and improve the patient experience, and has received extensive attention from academic and industrial circles in recent years. This paper aims to provide a comprehensive introduction to the key technologies, latest research progress, current clinical application status, and future development opportunities and challenges of intelligent blood collection robots. The paper introduces the key technologies that can achieve autonomous blood collection, including blood vessel recognition and positioning technology, mechanical arm design, and puncture control technology. Among them, blood vessel recognition and positioning is one of the key supporting technologies for intelligent blood collection, which can be realized by using technologies such as machine vision, near-infrared imaging, and ultrasound imaging. In addition, the paper also introduces some existing commercial intelligent blood collection robots and their clinical application cases in hospitals. Finally, we analyze the future application prospects and challenges of intelligent blood collection robots.

15 January 2026 in Frontiers in Medicine
Verified
Journal Article
Open access
PDF file
YWYaqing Wang
Yaqing Wang
YJYue Jiang
Yue Jiang
WJWen Jin
Wen Jin
YXYijun Xu
Yijun Xu
WLWeinan Lin
Weinan Lin
ZFZhaoxi Fang
Zhaoxi Fang
In recent years, large language models (LLMs) have achieved remarkable progress in natural language processing and demonstrated potential applications in medicine. However, their professional capabilities in specific medical subfields, such as immunology, still require systematic evaluation. This study systematically evaluated 11 representative LLMs, including DeepSeek, GPT, Llama, Gemma, and Qwen series, based on the Chinese National Health Professional Qualification Examination in Rheumatology and Clinical Immunology. The evaluation covered four dimensions: basic medical knowledge, related medical knowledge, immunology knowledge, and professional practice ability. Results show significant differences among LLMs. DeepSeek-R1 and Qwen3 achieve the best performance, with accuracy exceeding 90%. However, performance on professional practice ability tasks remained relatively low, highlighting limitations in complex clinical applications.

1 August 2026 in Sensors
Verified
Journal Article
Open access
PDF file
WSWenjie Su
Wenjie Su
EFEn Fan
En Fan
JWJilong Wang
Jilong Wang
SLSi Yu Lin
Si Yu Lin
ZFZhaoxi Fang
Zhaoxi Fang
Solder-joint detection and localization on large, complex printed circuit boards (PCBs) remain challenging because PCB images often contain unevenly distributed features, nonuniform illumination, specular reflection, scale variation and geometric distortion. Conventional SIFT-based registration methods usually use fixed matching parameters and therefore cannot adapt well to regions with different component densities. To address this limitation, this study proposes a hardware–software integrated PCB image registration framework that combines a robotic end effector with a locally adaptive K-nearest neighbor (LAKNN) strategy and SIFT descriptors. The hardware platform provides stable image acquisition through a lifting mechanism and ring-light illumination, while the software module adjusts the neighbor-search space according to local feature density and matching confidence. Experimental results show that the proposed LAKNN method achieves 90.8% inlier-match accuracy in the ablation experiment and improves registration robustness under height, region and viewpoint variations. The proposed framework provides a practical basis for automated PCB inspection and robotic soldering alignment.

26 June 2026 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
YJYue Jiang
Yue Jiang
ZDZhenzhong Dai
Zhenzhong Dai
WJWen Jin
Wen Jin
WLWeinan Lin
Weinan Lin
YXYijun Xu
Yijun Xu
ZFZhaoxi Fang
Zhaoxi Fang
With the rapid advancement of artificial intelligence technology, large language models (LLMs) have shown considerable potential in the medical field. This study systematically evaluated the performance of five multimodal LLMs, including GPT-4o, Llama4Scout, Gemma3-27B, Qwen3-VL235B, and DeepSeek-VL2, in medicinal plant image recognition tasks. We selected 200 medicinal plant images from a privately copyrighted dataset and tested the models using a four-choice format to evaluate their recognition accuracy. Results indicate that Qwen3-VL-235B demonstrated the highest accuracy at 90.50%, outperforming other models. GPT-4o ranked second at 85.00%, while Gemma3-27B, Llama4Scout, and DeepSeek-VL2 achieved 65.50%, 58.50%, and 58.00%, respectively. These findings indicate that multimodal LLMs hold promising potential for medicinal plant recognition, yet further optimization for specific domains is required to enhance accuracy.

16 March 2026 in Frontiers in Medicine
Verified
Journal Article
Open access
PDF file
YWYaqing Wang
Yaqing Wang
YJYue Jiang
Yue Jiang
WJWen Jin
Wen Jin
WLWeinan Lin
Weinan Lin
YXYijun Xu
Yijun Xu
ZFZhaoxi Fang
Zhaoxi Fang
Large language models (LLMs) have shown growing applications in medicine, yet their capabilities in the field of clinical laboratory technology remain underexplored. This study aims to evaluate the performance of LLMs in the Chinese Clinical Laboratory Technologist Qualification Examination (CCLTQE) and provide empirical evidence for their application in laboratory medicine. A dataset containing 1,600 single-choice questions is constructed for the CCLTQE exam. The dataset covers four sections: clinical laboratory fundamentals, other medical knowledge related to clinical laboratory technology, clinical laboratory specialized knowledge, and clinical laboratory professional practice competence. We select 12 LLMs for evaluation, including the DeepSeek, GPT, Llama, Qwen, and Gemma series. Results show that Qwen3-235B achieves the highest overall accuracy (89.93%), followed by DeepSeek-R1 (89.75%) and QwQ-32B (89.22%). This study demonstrates that LLMs optimized for Chinese language and domain-specific content demonstrate outstanding performance in CCLTQE, indicating significant potential for AI-assisted education and practice in laboratory medicine.