Differencing Time Series as an Important Feature Extraction for Intradialytic Hypotension Prediction using Machine Learning

Jiun Yi Yang, Hsiang Wei Hu, Chih Hao Liu, Kuan Yu Chen, Chi Hin Un, Chih Chiang Huang, Chou Cheng Chen, Chou Ching K. Lin, Hsuan Chang, Hsuan Ming Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Intradialytic hypotension (IDH) needs a real-time early warning system. Thus, the goal of the research is to design time-series differences of the features of IDH to increase the performance of the warning system. We created two new features called the time-relevant difference. These features were calculated by the current value minus the previous three values. The result showed a sensitivity of 88.9% and a specificity of 85.1%. Using the LightGBM, the sensitivity was 73.8%, and the specificity was 67.9%. Time series differences generated new eigenvalues for the model system for training of non-RNN-type algorithms to obtain acceptable values.

Original languageEnglish
Title of host publication3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2021
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages19-20
Number of pages2
ISBN (Electronic)9781728193045
DOIs
Publication statusPublished - 2021
Event3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2021 - Tainan, Taiwan
Duration: 2021 May 282021 May 30

Publication series

Name3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2021

Conference

Conference3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2021
Country/TerritoryTaiwan
CityTainan
Period21-05-2821-05-30

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Renewable Energy, Sustainability and the Environment
  • Biomedical Engineering
  • Safety, Risk, Reliability and Quality
  • Building and Construction
  • Health Policy
  • Health(social science)

Fingerprint

Dive into the research topics of 'Differencing Time Series as an Important Feature Extraction for Intradialytic Hypotension Prediction using Machine Learning'. Together they form a unique fingerprint.

Cite this