Timeseries representation learning for EHR

Title Timeseries representation learning for EHR
Summary Timeseries representation learning for Electronic Health Records
Keywords Timeseries data, Electronic Health Records, Representation Learning
References Data: https://mimic.mit.edu/docs/about/

Papers: https://arxiv.org/pdf/1907.05321.pdf https://www.ijcai.org/proceedings/2021/0324.pdf https://proceedings-of-deim.github.io/DEIM2022/papers/H23-4.pdf https://proceedings.neurips.cc/paper/2019/file/53c6de78244e9f528eb3e1cda69699bb-Paper.pdf

Supervisor Amira Soliman, Stefan Byttner, Kobra Etminani, Omar Hamed, Ali Amirahmadi
Level Master
Status Open

The use of Electronic Health Records (EHR) is increasing in both research and clinical practice to enhance the ability to provide the needed care to patients without posing additional economic burdens. Patient data is considered temporal data that is being measured over time. EHR data is complex and sparse therefore challenging to model. In this master thesis, the objective is to investigate the state-of-the-art techniques for representation learning of temporal data and compare their impact on target machine learning tasks using EHR data. Example of research questions: How time affects representation space? How to handle irregular timescales?