We create and study methods and tools to support applications of artificial intelligence in health with a focus on unstructured clinical data reuse. Reuse of clinical data is essential to fulfill the promises for high quality healthcare, improved healthcare management, and effective clinical research. Accurate and detailed clinical information, as found in patient Electronic Health Records (EHR), rather than existing but often biased and insufficiently detailed diagnostic and procedure codes assigned for reimbursement and administrative purposes only are needed for effective clinical research and high quality and efficient healthcare. We use Natural Language Processing (NLP) to extract this clinical information from EHRs, and to automatically de-identifying clinical notes and protect patient privacy, also providing user-friendly and easy to use tools for researchers and clinicians to browse, query, visualize, and obtain clinical data. The research group is lead by Stephane Meystre and was part of the Department of Biomedical Informatics at the University of Utah, then of the Biomedical Informatics Center (BMIC) at the Medical University of South Carolina, and now with the OnePlanet Research Center and partnering universities (Radboud University Medical Center mostly) in The Netherlands.