个人简介

周伟鹏，南方科技大学公共卫生及应急管理学院助理教授。本科毕业于美国威斯康星大学麦迪逊分校，获计算机科学与统计学学士学位；博士毕业于美国华盛顿大学，获生物医学信息学博士学位；随后在美国耶鲁大学从事博士后研究。 

主要从事医学人工智能、医学自然语言处理与公共卫生信息学研究，重点关注临床文本智能解析、电子健康记录表型识别、大语言模型在医疗与公共卫生场景中的适配与评估、生物医学文献挖掘，以及疾病与伤害监测预警。相关成果发表于 *Journal of the American Medical Informatics Association*、*JAMIA Open*、*JMIR Mental Health*、*Annual Review of Biomedical Data Science* 等期刊，并在 AMIA 等医学信息学会议展示。

研究方向

1. 临床文本智能解析与电子健康记录表型识别：研究临床记录章节识别、症状与医学实体抽取、长新冠患者识别等方法，提升非结构化医疗数据的可用性。

2. 医疗大语言模型的方法与评价：研究大语言模型在临床自然语言处理和公共卫生任务中的适配、泛化、评价及真实场景部署问题。

3. 生物医学文献挖掘与公共卫生监测：利用自然语言处理和机器学习方法开展生物医学数据集发现、环境暴露研究分析，以及疾病和伤害监测预警。

教育经历

2019/09-2024/08，华盛顿大学西雅图分校，生物医学信息学，博士 

2015/09-2019/06，威斯康星大学麦迪逊分校，计算机科学与统计学，学士

工作经历

2026/09至今，南方科技大学公共卫生及应急管理学院，助理教授  

2024/09-2026/08，美国耶鲁大学，博士后研究员  

2023/06-2023/09，美国哈佛医学院及波士顿儿童医院儿科系，暑期实习

2022/06-2022/09，美国哈佛医学院及波士顿儿童医院儿科系，暑期实习

科研项目

1. University of Washington Institute for Medical Data Science，2023-2024 Pilot Award，“Towards Automatic Identification of Patients in Need of Long COVID Care with Natural Language Processing Methods”，主持，2023-2025。

2. National Institutes of Health，The Small Business Innovation Research Program，“Assessing Immunology Dataset Quality Through Literature Mining”，参与，2025-2026。

3. National Institutes of Health，R24ES036135，“Accelerating Data and Metadata Standards in the Environmental Health Sciences Study of Emerging Water Contaminants”，参与，2024-2026。

4. Yale-Mayo Clinic FDA Center of Excellence in Regulatory Science and Innovation，“A Machine-Learning Model to Identify Women with Anti-Nuclear Antibody Related Connective Tissue Diseases”，参与，2026。

5. Washington Traffic Safety Commission，“Trends of Aggressive Driving in Washington”，参与，2026。

6. University of Washington Foundation，2024 Transformation Grants for IDD Research，“Data Platform for Children and Young Adults with Intellectual and/or Developmental Disability”，参与，2026。

代表性论文（#共同一作，*通讯作者）

1. Zhou W, Burford KG, Itzkowitz NG, deGrauw X, Patel KV, Rundle A, Mooney SJ. Towards Automatic Analysis of Clinical Notes for Injuries of Bicycles and Other Micromobility Devices Using Natural Language Processing. Injury Prevention. Published online October 6, 2026. doi:10.1136/ip-2025-045761

2. Zhou W, Guo Y, Kinfe BN, Zhen E, Giuffrè M, Xu H, Ding H, Raja K. Automated Recognition of Diverse Immunology Datasets in Full-text Articles. Poster accepted for presentation at the AMIA 2026 Annual Symposium, 2026.

3. Zhou W, Keloth VK, Wang R, Michel G, Rajeevan H, Zhang C, Gossett E, Xu H, Deziel NC, Cheung K-H. Literature Visualization of the Shifting PFAS Exposure Research Landscape. Poster presented at the AMIA 2025 Annual Symposium, 2025.

4. Zhou W, Yang G, Shi R, Li A, Ai X, Chen Q, Hu Y, Xu H, Miller TA. Bridging the Development-Implementation Gap in Clinical NER: An Empirical Study on Input Length Effects for Real-World Deployment. Poster presented at the AMIA 2025 Annual Symposium, 2025.

5. Zhou W, Gentile N, Miller T, Stephens K, Yetisgen M. Identifying Long COVID Patients from Primary Care Clinics and Long COVID Specialty Care Clinic with Natural Language Processing. Poster presented at the AMIA 2025 Informatics Summit, 2025.

6. Zhou W, Gentile N, Miller T, Yetisgen M, Stephens KA. Comparing Long COVID Patients from Primary Care Clinics and Long COVID Specialty Care Clinic with Natural Language Processing. Poster presented at the AMIA 2025 Informatics Summit, 2025.

7. Zhou W, Youngbloom A, Ren X, Saelens BE, Mooney SD, Mooney SJ. The Automatic Context Measurement Tool (ACMT) to Compile Participant-Specific Built and Social Environment Measures for Health Research: Development and Usability Study. JMIR Formative Research. 2024;8:e56510. doi:10.2196/56510

8. Zhou W, Miller TA. Generalizable Clinical Note Section Identification with Large Language Models. JAMIA Open. 2024;7(3):ooae075. doi:10.1093/jamiaopen/ooae075

9. Zhou W, Fong C, Zhou S, Yetisgen M, Chatterjee N. Symptom Trajectories Prior to Out-of-Hospital Cardiac Arrest: Insights from Natural Language Processing. Presented at the AMIA 2024 Informatics Summit, 2024.

10. Zhou W, Yetisgen M, Afshar M, Gao Y, Savova G, Miller TA. Improving Model Transferability for Clinical Note Section Classification Models Using Continued Pretraining. Journal of the American Medical Informatics Association. 2024;31(1):89-97. doi:10.1093/jamia/ocad190

11. Zhou W, Prater LC, Goldstein EV, Mooney SJ. Identifying Rare Circumstances Preceding Female Firearm Suicides: Validating a Large Language Model Approach. JMIR Mental Health. 2023;10:e49359. doi:10.2196/49359

12. Zhou W, Afshar M, Dligach D, Gao Y, Miller TA. Improving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles. In: Proceedings of the 5th Clinical Natural Language Processing Workshop. 2023:125-130. ACL Anthology