Deriving Insights from Electronic Health Records Using Machine Learning: Challenges and Opportunities
Li-wei Lehman
Massachusetts Institute of Technology, USA
DEIB - Conference Room "Emilio Gatti" (building 20)
June 21st, 2018
17.30 am
Contacts:
Riccardo Barbieri
Research Line:
Analysis of biological systems and e-health
Massachusetts Institute of Technology, USA
DEIB - Conference Room "Emilio Gatti" (building 20)
June 21st, 2018
17.30 am
Contacts:
Riccardo Barbieri
Research Line:
Analysis of biological systems and e-health
Abstract
PhysioNet is an NIH-funded research resource intended to stimulate current research and new investigations in the study of complex biomedical and physiologic signals. It is one of the four NIH-supported initiatives highlighted recently in a White House blog entry about accelerating the pace of discovery through the use of Big Data. The MIMIC III Database, distributed freely via PhysioNet, contains physiologic signals and vital signs time series captured from patient monitors, and comprehensive clinical data obtained from hospital medical information systems, for tens of thousands of Intensive Care Unit (ICU) patients. In this talk, I will present past and on-going research projects applying machine learning techniques to learn shared representations with prognostic values from physiological time series and clinical data using the MIMIC III database. I will also discuss opportunities and challenges in deriving insights from large-scale observational data, such as MIMIC III, using machine learning.
Endorsed by MISTI – MIT-Italy Program – Fondazione Rocca - IEEE Italian Chapter EMB
Endorsed by MISTI – MIT-Italy Program – Fondazione Rocca - IEEE Italian Chapter EMB
Short Bio
Dr. Li-wei Lehman is a research scientist in the Laboratory for Computational Physiology (LCP) at the MIT Institute for Medical Engineering and Science. She is a member of the NIHfunded project Research Resource for Complex Physiologic Signals (PhysioNet). Her research activities focus on application of machine learning techniques to physiological time series and clinical data for patient monitoring and outcome prediction. She received her Master’s degree in Computer Science from Georgia Institute of Technology, and her Ph.D from MIT in June 2005.