Cargando…

PLAAN: Pain Level Assessment with Anomaly-detection based Network

Automatic chronic pain assessment and pain intensity estimation has been attracting growing attention due to its widespread applications. One of the prevalent issues in automatic pain analysis is inadequate balanced expert-labelled data for pain estimation. This work proposes an anomaly detection ba...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yi, Ghosh, Shreya, Joshi, Jyoti
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7786324/
http://dx.doi.org/10.1007/s12193-020-00362-8
_version_ 1783632602878443520
author Li, Yi
Ghosh, Shreya
Joshi, Jyoti
author_facet Li, Yi
Ghosh, Shreya
Joshi, Jyoti
author_sort Li, Yi
collection PubMed
description Automatic chronic pain assessment and pain intensity estimation has been attracting growing attention due to its widespread applications. One of the prevalent issues in automatic pain analysis is inadequate balanced expert-labelled data for pain estimation. This work proposes an anomaly detection based network addressing one of the existing limitations of automatic pain assessment. The evaluation of the network is performed on pain intensity estimation and protective behaviour estimation tasks from body movements in the EmoPain Challenge dataset. The EmoPain dataset consists of body part based sensor data for both the tasks. The proposed network, PLAAN (Pain Level Assessment with Anomaly-detection based Network), is a lightweight LSTM-DNN network which considers features based on sensor data as the input and predicts intensity level of pain and presence or absence of protective behaviour in chronic low back pain patients. Joint training considering body movement patterns, such as exercise type, corresponding to pain exhibition as a label improves the performance of the network. However, contrary to perception, protective behaviour rather exists sporadically alongside pain in the EmoPain dataset. This induces yet another complication in accurate estimation of protective behaviour. This problem is resolved by incorporating anomaly detection in the network. A detailed comparison of different networks with varied features is outlined in the paper, presenting a significant improvement with the final proposed anomaly detection based network.
format Online
Article
Text
id pubmed-7786324
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Springer International Publishing
record_format MEDLINE/PubMed
spelling pubmed-77863242021-01-06 PLAAN: Pain Level Assessment with Anomaly-detection based Network Li, Yi Ghosh, Shreya Joshi, Jyoti J Multimodal User Interfaces Original Paper Automatic chronic pain assessment and pain intensity estimation has been attracting growing attention due to its widespread applications. One of the prevalent issues in automatic pain analysis is inadequate balanced expert-labelled data for pain estimation. This work proposes an anomaly detection based network addressing one of the existing limitations of automatic pain assessment. The evaluation of the network is performed on pain intensity estimation and protective behaviour estimation tasks from body movements in the EmoPain Challenge dataset. The EmoPain dataset consists of body part based sensor data for both the tasks. The proposed network, PLAAN (Pain Level Assessment with Anomaly-detection based Network), is a lightweight LSTM-DNN network which considers features based on sensor data as the input and predicts intensity level of pain and presence or absence of protective behaviour in chronic low back pain patients. Joint training considering body movement patterns, such as exercise type, corresponding to pain exhibition as a label improves the performance of the network. However, contrary to perception, protective behaviour rather exists sporadically alongside pain in the EmoPain dataset. This induces yet another complication in accurate estimation of protective behaviour. This problem is resolved by incorporating anomaly detection in the network. A detailed comparison of different networks with varied features is outlined in the paper, presenting a significant improvement with the final proposed anomaly detection based network. Springer International Publishing 2021-01-06 2021 /pmc/articles/PMC7786324/ http://dx.doi.org/10.1007/s12193-020-00362-8 Text en © The Author(s), under exclusive licence to Springer Nature Switzerland AG part of Springer Nature 2021 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Original Paper
Li, Yi
Ghosh, Shreya
Joshi, Jyoti
PLAAN: Pain Level Assessment with Anomaly-detection based Network
title PLAAN: Pain Level Assessment with Anomaly-detection based Network
title_full PLAAN: Pain Level Assessment with Anomaly-detection based Network
title_fullStr PLAAN: Pain Level Assessment with Anomaly-detection based Network
title_full_unstemmed PLAAN: Pain Level Assessment with Anomaly-detection based Network
title_short PLAAN: Pain Level Assessment with Anomaly-detection based Network
title_sort plaan: pain level assessment with anomaly-detection based network
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7786324/
http://dx.doi.org/10.1007/s12193-020-00362-8
work_keys_str_mv AT liyi plaanpainlevelassessmentwithanomalydetectionbasednetwork
AT ghoshshreya plaanpainlevelassessmentwithanomalydetectionbasednetwork
AT joshijyoti plaanpainlevelassessmentwithanomalydetectionbasednetwork