Skip to Content
SBMI Horizontal Logo

Dr. Kai Zhang is an Assistant Professor at the McWilliams School of Biomedical Informatics at UTHealth Houston. He is also an integral member of the Center for Secure Artificial Intelligence For Healthcare (SAFE). Dr. Zhang specializes in AI fairness, multimodal learning, and causality. He has been honored with opportunities to review manuscripts for renowned journals such as JBI, The Lancet Digital Health, Journal of Medical Internet Research, Journal of Medical Virology, IEEE TCOM, IEEE IT, and IEEE Access Journal. He has served on the reviewer board for IEEE ISIT in 2021 and IEEE JSAC in 2018.

Dr. Zhang has contributed research to prestigious journals, including but not limited to JBI, AMIA, Journal of Thrombosis and Thrombolysis, JMIR Medical Informatics, PLOS Digital Health, and Critical Care Medicine. His expertise also extends to the domain of information theory, with publications in IEEE TCOM, IEEE ISIT, and IEEE JSAC. He has co-authored a distinguished paper that was nominated as a finalist for the AMIA 2023 Best Student Paper Award. He is also an active member of several professional organizations, including the American Medical Informatics Association (AMIA), the Institute for Healthcare Improvement, and the Institute of Electrical and Electronics Engineers (IEEE).

  • Tell us about your research center and/or what research/work you are currently working on?
    My current research is mainly around AI Fairness, Multimodal learning, healthcare predictive modeling, and large language models and their application in healthcare.
  • What type of student or Postdoctoral Fellow are you looking for to work in your center?
    Highly self-motivated and have a strong computer science background.
  • What does the future of your research look like?
    I plan to extend my work on model fairness to encompass a broader array of healthcare applications, ensuring that AI systems make unbiased and equitable decisions. I will continue to tackle the challenges posed by data missingness and heterogeneities in multi-modal Electronic Health Records (EHR). In the realm of causality, I am excited about deploying our scalable causal structure learning algorithm in wider healthcare contexts, such as identifying risk factors for chronic diseases or understanding patient outcomes in clinical trials.
  • What does the future of informatics look like?
    In healthcare, the use of AI and machine learning for predictive modeling will continue to evolve. Model fairness will be a strong focus to ensure equitable healthcare delivery. The integration of multi-modal data sources, including EHR, genomics, imaging, and even social determinants of health, will enable a more comprehensive understanding of patient health and disease progression.

    Moreover, advancements in Natural Language Processing (NLP), especially large language models (LLMs) will revolutionize the way we understand and utilize unstructured data, like clinical notes, leading to more accurate diagnoses and personalized treatment plans.


  • Ph.D., Texas A&M University, 2020
  • M.S., Beijing Institute of Technology, 2015
  • B.S., Shandong University of Science and Technology, 2012

Areas of Expertise

  • Predictive modeling
  • Machine Learning for Healthcare
  • Fairness in Machine Learning

Staff Support

Shay Price | 713-500-3983