I am a Research Assistant Professor in the Department of Biomedical Informatics (DBMI) at Vanderbilt University Medical Center (VUMC). I earned my Ph.D. in Computer Science (2012) from the Chinese Academy of Sciences.
My research interests include leveraging AI, machine learning, data mining, natural language processing (NLP), and blockchain for enhancing precision medicine, with an emphasis on developing new algorithms on large health data to improve deep phenotyping, uncover knowledge, and improve accuracy and fairness for disease prediction. I am interested in research topics including model explanation, uncertainty measurement, and fairness.
Publications
Integration of Omics and Phenotypic Data for Precision Medicine
Juan Zhao, QiPing Feng, Wei-Qi Wei
Methods in Molecular Biology (Clifton, N.J.), vol. 2486, 2022, pp. 19--35
Jacy T. Zanussi, Juan Zhao, Chad A. Dorn, Ge Liu, QiPing Feng, WeiQi Wei, Jonathan D. Mosley, C. Michael Stein, Vivian K. Kawai
Clinical Pharmacology and Therapeutics, vol. 111, 2022 Feb, pp. 435--443
Natural language processing to identify lupus nephritis phenotype in electronic health records
Yu Deng, Jennifer A. Pacheco, Anh Chung, Chengsheng Mao, Joshua C. Smith, Juan Zhao, Wei-Qi Wei, April Barnado, Chunhua Weng, Cong Liu, Adam Cordon, Jingzhi Yu, Yacob Tedla, Abel Kho, Rosalind Ramsey-Goldman, Theresa Walunas, Yuan Luo
2021 Dec
American Heart Association Precision Medicine Platform Addresses Challenges in Data Sharing
Laura M. Stevens, James A. de Lemos, Sandeep R. Das, Christine Rutan, Heather M. Alger, Mitchell S.V. Elkind, Juan Zhao, Kritika Iyer, C. Alberto Figueroa, Jennifer L. Hall
Circulation: Cardiovascular Quality and Outcomes, vol. 14, 2021 Sep, pp. e007949
Machine Learning Challenges in Pharmacogenomic Research
Wei-Qi Wei, Juan Zhao, Dan M. Roden, Josh F. Peterson
Clinical Pharmacology and Therapeutics, vol. 110, 2021 Sep, pp. 552--554
View all
Projects
Using NLP on unstructured EHR for COVID-19 surveillance
We applied NLP pipeline and developed association analysis called ConceptWAS to track early symptoms for COVID-19
We developed machine learning and deep learning models to predict 10-year CVD risk using longitudinal EHR and genetic data.
Deep phenotyping using unsupervised machine learning
Applied a state-of-arts tensor factorization method to longitudinal EHR data