报告题目：Clinical Data Preprocessing – lessons learned from real cases
报告时间：2019年6月19日下午4:00
报告地点：校本部计算机楼212
报告人：Jin Chen教授(美国University of Kentucky)
Abstract：
Clinical data are first-hand medical data acquired from clinical centers either during the course of ongoing patient care or as part of a formal clinical trial program. While extracting the detailed phenotypes from clinical data is critical towards precision medicine, which aims to provide the best available care for each patient based on stratification into disease subclasses with a common biological basis of disease, the phenotypic descriptions in clinical data are often imprecise and incomplete, making them difficult to use directly. Clinical data preprocessing becomes an essential step in clinical data analysis. Failure of doing so put the comprehensive disease diagnosis, prognosis, as well as the translation of knowledge into clinical care into risk, as it depends critically upon high-quality clinical data. In this talk, I will use several real cases in our practice, including EHR feature extraction, medical imaging, and brain signaling, to demonstrate the importance of clinical data preprocessing, and to share the lessons learned during the course. Finally, I will discuss the current challenges in deep phenotyping including semantic and technical standards for phenotype and disease data.
Biography：
Jin Chen is an associate professor and interim chief of the Division of Biomedical Informatics, Department of Internal Medicine, Department of Computer Science, University of Kentucky. His work focuses on machine learning and its application on biomedical informatics. He has published more than 70 papers in the domain of computer science, informatics, biology, and medicine. His research is supported by DOE, NSF, and NIH.
