Improving Quality of Observational Streaming Medical Data by Using Long Short-Term Memory Networks (LSTMs)

Conference · Sun Apr 01 00:00:00 EDT 2018

DOI:https://doi.org/10.1109/ICDEW.2018.00015· OSTI ID:1463983

Bowie, Michael B. ^[1]; Begoli, Edmon  ^[1]; Park, Byung  ^[1]

---

1. ORNL

We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Science (SC)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1463983
• Resource Relation: Conference: IEEE International Conference on Data Engineering (ICDEW 2018) - Paris, , France - 4/16/2018 8:00:00 AM-4/19/2018 8:00:00 AM
• Country of Publication: United States
• Language: English