报告时间：2020年11月16日上午9:00-10:00

报告形式：腾讯会议

报告嘉宾：林毓聪

报告主题：High-throughput medical knowledge mining from large-scale texts and electronic healthcare records

Medical knowledge are the core components of medical knowledge graphs, which are needed for healthcare artificial intelligence. However, the requirement of expert annotation by conventional algorithm development processes creates a major bottleneck for mining new relations. In this lecture, I will present Hi-RES, a framework for high-throughput relation extraction algorithm development. We also show that combining knowledge articles with electronic health records (EHRs) significantly increases the classification accuracy. Furthermore, I will also introduce some ongoing projects includes EHR knowledge mining from EHR and automatic diagnosis framework, to show the enormous potential in medical knowledge mining.

林毓聪，清华大学统计学研究中心博士，哈佛医学院蔡天西教授组访问学者。主要研究方向有医学信息学、医学知识挖掘与图谱构建、自然语言模型构建、神经网络建模等。主要工作发表在医学信息学一区期刊Journal of Biomedical Informatics, BMC Medical Informatics and Decision Making与核心会议IEEE International Conference on Healthcare Informatics中。

李伟，中国人民大学统计学院，生物统计与流行病学讲师，北京大学数学科学学院博士。主要研究领域为因果推断、缺失数据、机器学习及高维统计等。目前已在包括Biometrika, Journal of Econometrics, Statistics in Medicine等国际著名统计期刊上发表多篇学术论文。主持一项中国博士后科学基金第66批面上项目，参与完成多项国家自然科学基金项目。