Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Fisioterapia em Movimento |
Texto Completo: | https://periodicos.pucpr.br/fisio/article/view/21584 |
Resumo: | Introduction:The shape-varying format of surface electromyograms introduces errors in the detection of contraction events. Objective: To investigate the accuracy and learning curves of inexperienced observers to detect the quantity of contraction events in surface electromyograms. Materials and methods: Six observers performed manual segmentation in 1200 shape-varying waveforms simulated using a phenomenological model with variable events, smooth changes in amplitude, marked on-off timing, and variable signal-to-noise ratio (0-39 dB). Segmentation was organized in four sessions with 15 blocks of 20 signals each. Accuracy and learning curves were modeled per block by linear and power regression models and tested for difference among sessions. Cut-off values of signal-to-noise ratio for optimal manual segmentation were also estimated. Results: The accuracy curve showed no significant linear trend throughout blocks and no difference among sessions 1-2-3-4 (87% [85; 89], 87% [85; 89], 87% [85; 89], 87% [81; 88]; p = 0.691). Accuracy was low for detection of 1 event (AUC = 0.40; sensitivity = 44%; specificity = 43%; cut-off = 12.9 dB) but was high and affected by the signal-to-noise ratio for detection of two events (AUC = 0.82; sensitivity = 77%; specificity = 76%; cut-off = 7.0 dB). The learning curve showed a significant power regression (p < 0.001) with decreasing values of learning percentages (time duration to complete the task) among sessions 1-2-3-4 (86.5% [68; 94], 76% [68; 91], 62% [38; 77], and 57% [52; 75]; p = 0.002). Conclusion: Inexperienced observers exhibit high, not trainable accuracy and a practice-dependent shortening in the time spent to detect the quantity of contraction events in simulated surface electromyograms. |
id |
PUC_PR-26_8186de4dacb758601d48a9d22ff309c3 |
---|---|
oai_identifier_str |
oai:ojs.periodicos.pucpr.br:article/21584 |
network_acronym_str |
PUC_PR-26 |
network_name_str |
Fisioterapia em Movimento |
repository_id_str |
|
spelling |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyogramsIntroduction:The shape-varying format of surface electromyograms introduces errors in the detection of contraction events. Objective: To investigate the accuracy and learning curves of inexperienced observers to detect the quantity of contraction events in surface electromyograms. Materials and methods: Six observers performed manual segmentation in 1200 shape-varying waveforms simulated using a phenomenological model with variable events, smooth changes in amplitude, marked on-off timing, and variable signal-to-noise ratio (0-39 dB). Segmentation was organized in four sessions with 15 blocks of 20 signals each. Accuracy and learning curves were modeled per block by linear and power regression models and tested for difference among sessions. Cut-off values of signal-to-noise ratio for optimal manual segmentation were also estimated. Results: The accuracy curve showed no significant linear trend throughout blocks and no difference among sessions 1-2-3-4 (87% [85; 89], 87% [85; 89], 87% [85; 89], 87% [81; 88]; p = 0.691). Accuracy was low for detection of 1 event (AUC = 0.40; sensitivity = 44%; specificity = 43%; cut-off = 12.9 dB) but was high and affected by the signal-to-noise ratio for detection of two events (AUC = 0.82; sensitivity = 77%; specificity = 76%; cut-off = 7.0 dB). The learning curve showed a significant power regression (p < 0.001) with decreasing values of learning percentages (time duration to complete the task) among sessions 1-2-3-4 (86.5% [68; 94], 76% [68; 91], 62% [38; 77], and 57% [52; 75]; p = 0.002). Conclusion: Inexperienced observers exhibit high, not trainable accuracy and a practice-dependent shortening in the time spent to detect the quantity of contraction events in simulated surface electromyograms.Editora PUCPRESS2017-09-15info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.pucpr.br/fisio/article/view/2158410.1590/S0103-51502013000300009Fisioterapia em Movimento (Physical Therapy in Movement); Vol. 26 No. 3 (2013)Fisioterapia em Movimento; v. 26 n. 3 (2013)1980-5918reponame:Fisioterapia em Movimentoinstname:Pontifícia Universidade Católica do Paraná (PUC-PR)instacron:PUC_PRenghttps://periodicos.pucpr.br/fisio/article/view/21584/20690Copyright (c) 2022 PUCPRESSinfo:eu-repo/semantics/openAccessde Sá Ferreira, ArthurSilva Guimarães, FernandoRibeiro Magalhães, Manuel ArmandoCoeli Souza e Silva, Regina2022-03-07T19:00:53Zoai:ojs.periodicos.pucpr.br:article/21584Revistahttps://periodicos.pucpr.br/fisioPRIhttps://periodicos.pucpr.br/fisio/oairubia.farias@pucpr.br||revista.fisioterapia@pucpr.br1980-59180103-5150opendoar:2022-03-07T19:00:53Fisioterapia em Movimento - Pontifícia Universidade Católica do Paraná (PUC-PR)false |
dc.title.none.fl_str_mv |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
title |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
spellingShingle |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms de Sá Ferreira, Arthur |
title_short |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
title_full |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
title_fullStr |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
title_full_unstemmed |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
title_sort |
Accuracy and learning curves of inexperienced observers for manual segmentation of electromyograms |
author |
de Sá Ferreira, Arthur |
author_facet |
de Sá Ferreira, Arthur Silva Guimarães, Fernando Ribeiro Magalhães, Manuel Armando Coeli Souza e Silva, Regina |
author_role |
author |
author2 |
Silva Guimarães, Fernando Ribeiro Magalhães, Manuel Armando Coeli Souza e Silva, Regina |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
de Sá Ferreira, Arthur Silva Guimarães, Fernando Ribeiro Magalhães, Manuel Armando Coeli Souza e Silva, Regina |
description |
Introduction:The shape-varying format of surface electromyograms introduces errors in the detection of contraction events. Objective: To investigate the accuracy and learning curves of inexperienced observers to detect the quantity of contraction events in surface electromyograms. Materials and methods: Six observers performed manual segmentation in 1200 shape-varying waveforms simulated using a phenomenological model with variable events, smooth changes in amplitude, marked on-off timing, and variable signal-to-noise ratio (0-39 dB). Segmentation was organized in four sessions with 15 blocks of 20 signals each. Accuracy and learning curves were modeled per block by linear and power regression models and tested for difference among sessions. Cut-off values of signal-to-noise ratio for optimal manual segmentation were also estimated. Results: The accuracy curve showed no significant linear trend throughout blocks and no difference among sessions 1-2-3-4 (87% [85; 89], 87% [85; 89], 87% [85; 89], 87% [81; 88]; p = 0.691). Accuracy was low for detection of 1 event (AUC = 0.40; sensitivity = 44%; specificity = 43%; cut-off = 12.9 dB) but was high and affected by the signal-to-noise ratio for detection of two events (AUC = 0.82; sensitivity = 77%; specificity = 76%; cut-off = 7.0 dB). The learning curve showed a significant power regression (p < 0.001) with decreasing values of learning percentages (time duration to complete the task) among sessions 1-2-3-4 (86.5% [68; 94], 76% [68; 91], 62% [38; 77], and 57% [52; 75]; p = 0.002). Conclusion: Inexperienced observers exhibit high, not trainable accuracy and a practice-dependent shortening in the time spent to detect the quantity of contraction events in simulated surface electromyograms. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-09-15 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.pucpr.br/fisio/article/view/21584 10.1590/S0103-51502013000300009 |
url |
https://periodicos.pucpr.br/fisio/article/view/21584 |
identifier_str_mv |
10.1590/S0103-51502013000300009 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://periodicos.pucpr.br/fisio/article/view/21584/20690 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2022 PUCPRESS info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2022 PUCPRESS |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Editora PUCPRESS |
publisher.none.fl_str_mv |
Editora PUCPRESS |
dc.source.none.fl_str_mv |
Fisioterapia em Movimento (Physical Therapy in Movement); Vol. 26 No. 3 (2013) Fisioterapia em Movimento; v. 26 n. 3 (2013) 1980-5918 reponame:Fisioterapia em Movimento instname:Pontifícia Universidade Católica do Paraná (PUC-PR) instacron:PUC_PR |
instname_str |
Pontifícia Universidade Católica do Paraná (PUC-PR) |
instacron_str |
PUC_PR |
institution |
PUC_PR |
reponame_str |
Fisioterapia em Movimento |
collection |
Fisioterapia em Movimento |
repository.name.fl_str_mv |
Fisioterapia em Movimento - Pontifícia Universidade Católica do Paraná (PUC-PR) |
repository.mail.fl_str_mv |
rubia.farias@pucpr.br||revista.fisioterapia@pucpr.br |
_version_ |
1799138746708262912 |