<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The relation between a biological process and the changes in passive electrical properties of the tissue is often non-linear, in which developing prediction models based on bioimpedance spectra is not trivial. Relevant information on tissue status may also lie in characteristic developments in the bioimpedance spectra over time, often neglected by conventional methods. The aim of this study was to explore possibilities in machine learning methods for time series of bioimpedance spectra, where we used organ ischemia as an example. Based on published data on the development of the bioimpedance spectrum during liver ischemia, a simulation model was made and used to generate sets of synthetic data with different levels of organ-to-organ variation, measurement noise and drift. Three types of artificial neural networks were employed in learning to predict the ischemic duration, based on the simulated datasets. The simulated prediction performance was very dependent on the amount of training examples, the organ-to-organ variation and the selection of input variables from the bioimpedance spectrum. The performance was also affected by noise and drift in the measurement, but a recurrent neural network with long short-term memory units could obtain good predictions even on noisy and drifting measurements. This approach may be relevant for further exploration on several applications of bioimpedance having the purpose of predicting a biological state based on spectra measured over time.</p></abstract>

The relation between a biological process and the changes in passive electrical properties of the tissue is often non-linear, in which developing prediction models based on bioimpedance spectra is not trivial. Relevant information on tissue status may also lie in characteristic developments in the bioimpedance spectra over time, often neglected by conventional methods. The aim of this study was to explore possibilities in machine learning methods for time series of bioimpedance spectra, where we used organ ischemia as an example. Based on published data on the development of the bioimpedance spectrum during liver ischemia, a simulation model was made and used to generate sets of synthetic data with different levels of organ-to-organ variation, measurement noise and drift. Three types of artificial neural networks were employed in learning to predict the ischemic duration, based on the simulated datasets. The simulated prediction performance was very dependent on the amount of training examples, the organ-to-organ variation and the selection of input variables from the bioimpedance spectrum. The performance was also affected by noise and drift in the measurement, but a recurrent neural network with long short-term memory units could obtain good predictions even on noisy and drifting measurements. This approach may be relevant for further exploration on several applications of bioimpedance having the purpose of predicting a biological state based on spectra measured over time.

Possibilities in the application of machine learning on bioimpedance time-series

Journal of Electrical Bioimpedance

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Possibilities in the application of machine learning on bioimpedance time-series"}

The relation between a biological process and the changes in passive electrical properties of the tissue is often non-linear, in which developing prediction...

Possibilities in the application of machine learning on bioimpedance time-series

Published Online: Jul 02, 2019

Page range: 24 - 33

Received: Nov 30, 2018

DOI: https://doi.org/10.2478/joeb-2019-0004

Keywords
Bioimpedance, time-series, machine learning, deep learning, ischemia

© 2019 Tronstad, Strand-Amundsen, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Possibilities in the application of machine learning on bioimpedance time-series

Published Online: Jul 02, 2019

Page range: 24 - 33

Received: Nov 30, 2018

DOI: https://doi.org/10.2478/joeb-2019-0004

KeywordsBioimpedance, time-series, machine learning, deep learning, ischemia

© 2019 Tronstad, Strand-Amundsen, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
Bioimpedance, time-series, machine learning, deep learning, ischemia