Dr. Jiang has received extensive training in machine learning and biomedical informatics, obtaining a Ph.D. from Carnegie Mellon University and completing a postdoctoral program at UC San Diego. He specializes in privacy-preserving data mining, federated learning, and co-teaching models for knowledge and data. Over the course of 15 years, Dr. Jiang has dedicated himself to bridging the gap between these two fields, focusing on developing innovative AI models tailored to the unique challenges of healthcare data, such as sparsity, errors, and missing information. His contributions have been recognized with multiple prestigious awards, including several best and distinguished paper awards from the American Medical Informatics Association (AMIA) Joint Summits on Translational Science in 2012, 2013, and 2016, as well as the AMIA annual symposium in 2020. In addition, Dr. Jiang has secured grants from the National Institutes of Health (NIH), including R00, R13, R21, R01, and U01 grants, and has been honored with career awards such as the CPRIT Rising Stars and UT Stars. He has also been the recipient of best and distinguished paper awards at the AMIA Annual Symposiums and the Joint Summits on Translational Science in 2012, 2013, 2016, and 2020. Furthermore, Dr. Jiang is actively involved in organizing the iDASH Genome Privacy competition since 2014, an event that has garnered attention from Nature News and GenomeWeb.
- Tell us about your research center and/or what research/work you are currently working on?
At the McWilliams School of Biomedical Informatics, I direct the Center for Secure Artificial Intelligence For Healthcare (SAFE). Our work involves integrating techniques from computer science, applied mathematics, biostatistics, medicine, and pharmacology to expedite biomedical data research and discovery.
I am also involved in a range of projects spanning various areas of health informatics and data science. These projects primarily focus on Alzheimer's disease, Multiple Chronic Conditions (MCC), genomic data sharing, clinical trials, cancer phenotyping, and computational phenotyping using multisite EHR data. The work includes developing combinatorial drug repositioning therapies, creating informatics frameworks, accelerating data sharing and collaboration with privacy protection, and harmonizing clinical trials. Additionally, I am involved in efforts to employ artificial intelligence for predicting clinical outcomes in ovarian cancer. Overall, these projects demonstrate a strong emphasis on leveraging advanced data analysis techniques and privacy-preserving methodologies to enhance understanding and treatment of complex health conditions.
- What type of student or Postdoctoral Fellow are you looking for to work in your center?
I am looking for highly self-motivated students or postdoctoral fellows who have a strong quantitative background and programming skills. They should have a keen interest in biomedical informatics and a willingness to delve into new areas of research. Experience or interest in fields such as machine learning, artificial intelligence, data science, biostatistics, or related fields would be beneficial. The ideal candidate would be someone who is not only technically proficient, but also has a strong interest in the application of these technologies to healthcare and biomedical research. They should be innovative thinkers, able to work independently and collaboratively, and have a deep commitment to advancing the state-of-the-art in secure AI for healthcare.
- What does the future of your research look like?
The future of my research would include developing more advanced and secure AI models for predicting and diagnosing diseases, creating personalized treatment plans, and improving the overall quality of patient care. I will also focus on developing new methods for protecting patient privacy while sharing and analyzing biomedical data. Another important aspect would be the integration of different types of biomedical data (e.g., genomic, clinical, and environmental data) to provide a more comprehensive understanding of health and disease. We also envision collaborating with other researchers, clinicians, and policymakers to ensure that our research findings can be effectively translated into clinical practice and health policies. Ultimately, my goal is to leverage the power of AI to make healthcare more predictive, personalized, and precise.
- What does the future of informatics look like?
The future of informatics, in my humble opinion, will be increasingly intertwined with real-world healthcare needs. We are likely to see a greater emphasis on personalized medicine, powered by advanced data analytics and AI technologies. Informatics will play a crucial role in integrating diverse health data sources, enabling more precise diagnoses, and helping create individualized treatment plans. The field will also need to address the pressing issues of data security and patient privacy, developing robust frameworks for secure data sharing and analysis. Moreover, it will provide the backbone for a more connected and collaborative healthcare system, fostering seamless interactions between patients, healthcare providers, researchers, and policymakers.
- What courses do you teach?
I teach BMI 5311 Foundation of Biomedical Informatics II, a course that provides students with a broad understanding of various topics in the field, including data analysis, machine learning, artificial intelligence, and their applications in healthcare.
- What major UTHealth Houston departments/institutes do you collaborate with?
I collaborate with several major UTHealth Houston departments including Anesthesia, Dental, Emergency, ENT, Neurology, Nursing, Psychiatry, Pulmonary and Critical Care, Institute on Aging, and the Stroke Institute.
Education
- PhD, 2010, Computer Science, Carnegie Mellon University
- MS, 2006, Computer Science, University of Iowa
- BS, 2003, Computer Science, Shanghai Maritime University
Areas of Expertise
- Healthcare privacy
- Biomedical data mining
- Computational phenotyping
