Evaluation of an algorithm to choose between competing models of respiratory mechanics
Model based decision support helps in optimizing therapy settings for individual patients while providing additional insight into a patient’s disease state through the identified model parameters. Using multiple models with different simulation focus and complexity allows adapting decision support t...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2015-09-01
|
Series: | Current Directions in Biomedical Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/cdbme-2015-0103 |
id |
doaj-92931d5a369f4a159671bd5213161348 |
---|---|
record_format |
Article |
spelling |
doaj-92931d5a369f4a159671bd52131613482021-09-06T19:19:22ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042015-09-011142843210.1515/cdbme-2015-0103cdbme-2015-0103Evaluation of an algorithm to choose between competing models of respiratory mechanicsKretschmer Jörn0Riedlinger Axel1Möller Knut2Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, GermanyInstitute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, GermanyInstitute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, GermanyModel based decision support helps in optimizing therapy settings for individual patients while providing additional insight into a patient’s disease state through the identified model parameters. Using multiple models with different simulation focus and complexity allows adapting decision support to the current clinical situation and the available data. A previously presented set of numerical criteria allows selecting the best model based on fit quality, model complexity, and how well the parameter values are defined by the presented data. To systematically evaluate those criteria in an algorithm we have created insilico data sets using four different respiratory mechanics models with three different parameter settings each. Each of those artificial patients was ventilated with three different manoeuvres and the resulting data was used to identify the same models used to create the data. The selection algorithm was then presented with the results to select the best model. Not considering determinateness of the identified model parameters, the algorithm chose the same model that was used to create the data in 78%, a more complex model in 5% and a less complex model in 18% of all cases. When including the determinateness of model parameters in the decision process, the algorithm chose the same model in 42% of the cases and a less complex model in 56% of all cases. In 2% of the presented cases, no model complied with the required criteria.https://doi.org/10.1515/cdbme-2015-0103medical decision supportphysiological modellingrespiratory mechanicsmodel selection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kretschmer Jörn Riedlinger Axel Möller Knut |
spellingShingle |
Kretschmer Jörn Riedlinger Axel Möller Knut Evaluation of an algorithm to choose between competing models of respiratory mechanics Current Directions in Biomedical Engineering medical decision support physiological modelling respiratory mechanics model selection |
author_facet |
Kretschmer Jörn Riedlinger Axel Möller Knut |
author_sort |
Kretschmer Jörn |
title |
Evaluation of an algorithm to choose between competing models of respiratory mechanics |
title_short |
Evaluation of an algorithm to choose between competing models of respiratory mechanics |
title_full |
Evaluation of an algorithm to choose between competing models of respiratory mechanics |
title_fullStr |
Evaluation of an algorithm to choose between competing models of respiratory mechanics |
title_full_unstemmed |
Evaluation of an algorithm to choose between competing models of respiratory mechanics |
title_sort |
evaluation of an algorithm to choose between competing models of respiratory mechanics |
publisher |
De Gruyter |
series |
Current Directions in Biomedical Engineering |
issn |
2364-5504 |
publishDate |
2015-09-01 |
description |
Model based decision support helps in optimizing therapy settings for individual patients while providing additional insight into a patient’s disease state through the identified model parameters. Using multiple models with different simulation focus and complexity allows adapting decision support to the current clinical situation and the available data. A previously presented set of numerical criteria allows selecting the best model based on fit quality, model complexity, and how well the parameter values are defined by the presented data. To systematically evaluate those criteria in an algorithm we have created insilico data sets using four different respiratory mechanics models with three different parameter settings each. Each of those artificial patients was ventilated with three different manoeuvres and the resulting data was used to identify the same models used to create the data. The selection algorithm was then presented with the results to select the best model. Not considering determinateness of the identified model parameters, the algorithm chose the same model that was used to create the data in 78%, a more complex model in 5% and a less complex model in 18% of all cases. When including the determinateness of model parameters in the decision process, the algorithm chose the same model in 42% of the cases and a less complex model in 56% of all cases. In 2% of the presented cases, no model complied with the required criteria. |
topic |
medical decision support physiological modelling respiratory mechanics model selection |
url |
https://doi.org/10.1515/cdbme-2015-0103 |
work_keys_str_mv |
AT kretschmerjorn evaluationofanalgorithmtochoosebetweencompetingmodelsofrespiratorymechanics AT riedlingeraxel evaluationofanalgorithmtochoosebetweencompetingmodelsofrespiratorymechanics AT mollerknut evaluationofanalgorithmtochoosebetweencompetingmodelsofrespiratorymechanics |
_version_ |
1717778761910321152 |