Machine learning for automatic identification of thoracoabdominal asynchrony in children

Background The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection). Methods To assess synchrony between the thor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pediatric research 2021-04, Vol.89 (5), p.1232-1238
Hauptverfasser: Ratnagiri, Madhavi V., Ryan, Lauren, Strang, Abigail, Heinle, Robert, Rahman, Tariq, Shaffer, Thomas H.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1238
container_issue 5
container_start_page 1232
container_title Pediatric research
container_volume 89
creator Ratnagiri, Madhavi V.
Ryan, Lauren
Strang, Abigail
Heinle, Robert
Rahman, Tariq
Shaffer, Thomas H.
description Background The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection). Methods To assess synchrony between the thorax and abdomen, the movements of the two compartments during quiet breathing were measured using pneu RIP. Fifty-one recordings were obtained: 20 were used to train a machine-learning (ML) model with elastic-net regularization, and 31 were used to test the model’s performance. Two feature sets were explored: (1) phase difference ( ɸ ) between the thoracic and abdominal signals and (2) inverse cumulative percentage (ICP), which is an alternate measure of data distribution. To compute accuracy of training, the model outcomes were compared with five experts’ assessments. Results Accuracies of 61.3% and 90.3% were obtained using ɸ and ICP features, respectively. The inter-rater reliability (i.r.r.) of the assessments of experts was 0.402 and 0.684 when they used ɸ and ICP to identify TAA, respectively. Conclusions With this pilot study, we show the efficacy of the ICP feature and ML in developing an accurate automated approach to identifying TAA that reduces time and effort for diagnosis. ICP also helped improve consensus among experts. Impact Our article presents an automated approach to identifying thoracic abdominal asynchrony using machine learning and the pneu RIP device. It also shows how a modified statistical measure of cumulative frequency can be used to visualize the progression of the pulmonary functionality along time. The pulmonary testing method we developed gives patients and doctors a noninvasive and easy to administer and diagnose approach. It can be administered remotely, and alerts can be transmitted to the physician. Further, the test can also be used to monitor and assess pulmonary function continuously for prolonged periods, if needed.
doi_str_mv 10.1038/s41390-020-1032-1
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10843835</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2526477800</sourcerecordid><originalsourceid>FETCH-LOGICAL-c428t-87748317e47a0dbb8c5896b8bd9cf42ca1753a2bb95d2325f627f4e95b9b75643</originalsourceid><addsrcrecordid>eNp1kUtLJDEUhYMo2rb-ADdDwI2b0jwrqZWI-ALFjYK7kKRS3ZGqxEmqhP73RtrHjOAq3NzvntycA8ABRscYUXmSGaYNqhBBValJhTfADHNabhgTm2CGEMUVbRq5A3ZzfkYIMy7ZNtihpCYIITEDT3faLn1wsHc6BR8WsIsJ6mmMgx69hb51YfSdt6WKAcYOjsuYtI3atHHwQfdQ51WwyxTDCvoAi1rfJhf2wFan--z2P845eLy8eDi_rm7vr27Oz24ry4gcKykEkxQLx4RGrTHSctnURpq2sR0jVmPBqSbGNLwllPCuJqJjruGmMYLXjM7B6Vr3ZTKDa21ZN-levSQ_6LRSUXv1fyf4pVrEV4WRZFRSXhSOPhRS_Du5PKrBZ-v6XgcXp6wII6i4Soks6OEP9DlOqZhQKE5qJoQsns8BXlM2xZyT6762wUi9B6fWwakS3HtNFC4zf_79xtfEZ1IFIGsgl1ZYuPT99O-qbwdipGQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2526477800</pqid></control><display><type>article</type><title>Machine learning for automatic identification of thoracoabdominal asynchrony in children</title><source>MEDLINE</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>Ratnagiri, Madhavi V. ; Ryan, Lauren ; Strang, Abigail ; Heinle, Robert ; Rahman, Tariq ; Shaffer, Thomas H.</creator><creatorcontrib>Ratnagiri, Madhavi V. ; Ryan, Lauren ; Strang, Abigail ; Heinle, Robert ; Rahman, Tariq ; Shaffer, Thomas H.</creatorcontrib><description>Background The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection). Methods To assess synchrony between the thorax and abdomen, the movements of the two compartments during quiet breathing were measured using pneu RIP. Fifty-one recordings were obtained: 20 were used to train a machine-learning (ML) model with elastic-net regularization, and 31 were used to test the model’s performance. Two feature sets were explored: (1) phase difference ( ɸ ) between the thoracic and abdominal signals and (2) inverse cumulative percentage (ICP), which is an alternate measure of data distribution. To compute accuracy of training, the model outcomes were compared with five experts’ assessments. Results Accuracies of 61.3% and 90.3% were obtained using ɸ and ICP features, respectively. The inter-rater reliability (i.r.r.) of the assessments of experts was 0.402 and 0.684 when they used ɸ and ICP to identify TAA, respectively. Conclusions With this pilot study, we show the efficacy of the ICP feature and ML in developing an accurate automated approach to identifying TAA that reduces time and effort for diagnosis. ICP also helped improve consensus among experts. Impact Our article presents an automated approach to identifying thoracic abdominal asynchrony using machine learning and the pneu RIP device. It also shows how a modified statistical measure of cumulative frequency can be used to visualize the progression of the pulmonary functionality along time. The pulmonary testing method we developed gives patients and doctors a noninvasive and easy to administer and diagnose approach. It can be administered remotely, and alerts can be transmitted to the physician. Further, the test can also be used to monitor and assess pulmonary function continuously for prolonged periods, if needed.</description><identifier>ISSN: 0031-3998</identifier><identifier>EISSN: 1530-0447</identifier><identifier>DOI: 10.1038/s41390-020-1032-1</identifier><identifier>PMID: 32620007</identifier><language>eng</language><publisher>New York: Nature Publishing Group US</publisher><subject>Abdomen ; Abdomen - physiopathology ; Adolescent ; Algorithms ; Automation ; Child ; Child, Preschool ; Clinical Research Article ; Computer Graphics ; Humans ; Machine Learning ; Medicine ; Medicine &amp; Public Health ; Observer Variation ; Pattern Recognition, Automated ; Pediatric Surgery ; Pediatrics ; Pilot Projects ; Plethysmography - instrumentation ; Plethysmography - methods ; Reproducibility of Results ; Respiration ; Respiratory Mechanics ; Respiratory Rate ; Signal Processing, Computer-Assisted ; Sleep Apnea Syndromes - diagnosis ; Thorax - physiopathology</subject><ispartof>Pediatric research, 2021-04, Vol.89 (5), p.1232-1238</ispartof><rights>International Pediatric Research Foundation, Inc 2020</rights><rights>International Pediatric Research Foundation, Inc 2020.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c428t-87748317e47a0dbb8c5896b8bd9cf42ca1753a2bb95d2325f627f4e95b9b75643</citedby><cites>FETCH-LOGICAL-c428t-87748317e47a0dbb8c5896b8bd9cf42ca1753a2bb95d2325f627f4e95b9b75643</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32620007$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ratnagiri, Madhavi V.</creatorcontrib><creatorcontrib>Ryan, Lauren</creatorcontrib><creatorcontrib>Strang, Abigail</creatorcontrib><creatorcontrib>Heinle, Robert</creatorcontrib><creatorcontrib>Rahman, Tariq</creatorcontrib><creatorcontrib>Shaffer, Thomas H.</creatorcontrib><title>Machine learning for automatic identification of thoracoabdominal asynchrony in children</title><title>Pediatric research</title><addtitle>Pediatr Res</addtitle><addtitle>Pediatr Res</addtitle><description>Background The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection). Methods To assess synchrony between the thorax and abdomen, the movements of the two compartments during quiet breathing were measured using pneu RIP. Fifty-one recordings were obtained: 20 were used to train a machine-learning (ML) model with elastic-net regularization, and 31 were used to test the model’s performance. Two feature sets were explored: (1) phase difference ( ɸ ) between the thoracic and abdominal signals and (2) inverse cumulative percentage (ICP), which is an alternate measure of data distribution. To compute accuracy of training, the model outcomes were compared with five experts’ assessments. Results Accuracies of 61.3% and 90.3% were obtained using ɸ and ICP features, respectively. The inter-rater reliability (i.r.r.) of the assessments of experts was 0.402 and 0.684 when they used ɸ and ICP to identify TAA, respectively. Conclusions With this pilot study, we show the efficacy of the ICP feature and ML in developing an accurate automated approach to identifying TAA that reduces time and effort for diagnosis. ICP also helped improve consensus among experts. Impact Our article presents an automated approach to identifying thoracic abdominal asynchrony using machine learning and the pneu RIP device. It also shows how a modified statistical measure of cumulative frequency can be used to visualize the progression of the pulmonary functionality along time. The pulmonary testing method we developed gives patients and doctors a noninvasive and easy to administer and diagnose approach. It can be administered remotely, and alerts can be transmitted to the physician. Further, the test can also be used to monitor and assess pulmonary function continuously for prolonged periods, if needed.</description><subject>Abdomen</subject><subject>Abdomen - physiopathology</subject><subject>Adolescent</subject><subject>Algorithms</subject><subject>Automation</subject><subject>Child</subject><subject>Child, Preschool</subject><subject>Clinical Research Article</subject><subject>Computer Graphics</subject><subject>Humans</subject><subject>Machine Learning</subject><subject>Medicine</subject><subject>Medicine &amp; Public Health</subject><subject>Observer Variation</subject><subject>Pattern Recognition, Automated</subject><subject>Pediatric Surgery</subject><subject>Pediatrics</subject><subject>Pilot Projects</subject><subject>Plethysmography - instrumentation</subject><subject>Plethysmography - methods</subject><subject>Reproducibility of Results</subject><subject>Respiration</subject><subject>Respiratory Mechanics</subject><subject>Respiratory Rate</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Sleep Apnea Syndromes - diagnosis</subject><subject>Thorax - physiopathology</subject><issn>0031-3998</issn><issn>1530-0447</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNp1kUtLJDEUhYMo2rb-ADdDwI2b0jwrqZWI-ALFjYK7kKRS3ZGqxEmqhP73RtrHjOAq3NzvntycA8ABRscYUXmSGaYNqhBBValJhTfADHNabhgTm2CGEMUVbRq5A3ZzfkYIMy7ZNtihpCYIITEDT3faLn1wsHc6BR8WsIsJ6mmMgx69hb51YfSdt6WKAcYOjsuYtI3atHHwQfdQ51WwyxTDCvoAi1rfJhf2wFan--z2P845eLy8eDi_rm7vr27Oz24ry4gcKykEkxQLx4RGrTHSctnURpq2sR0jVmPBqSbGNLwllPCuJqJjruGmMYLXjM7B6Vr3ZTKDa21ZN-levSQ_6LRSUXv1fyf4pVrEV4WRZFRSXhSOPhRS_Du5PKrBZ-v6XgcXp6wII6i4Soks6OEP9DlOqZhQKE5qJoQsns8BXlM2xZyT6762wUi9B6fWwakS3HtNFC4zf_79xtfEZ1IFIGsgl1ZYuPT99O-qbwdipGQ</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>Ratnagiri, Madhavi V.</creator><creator>Ryan, Lauren</creator><creator>Strang, Abigail</creator><creator>Heinle, Robert</creator><creator>Rahman, Tariq</creator><creator>Shaffer, Thomas H.</creator><general>Nature Publishing Group US</general><general>Nature Publishing Group</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8C1</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20210401</creationdate><title>Machine learning for automatic identification of thoracoabdominal asynchrony in children</title><author>Ratnagiri, Madhavi V. ; Ryan, Lauren ; Strang, Abigail ; Heinle, Robert ; Rahman, Tariq ; Shaffer, Thomas H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c428t-87748317e47a0dbb8c5896b8bd9cf42ca1753a2bb95d2325f627f4e95b9b75643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Abdomen</topic><topic>Abdomen - physiopathology</topic><topic>Adolescent</topic><topic>Algorithms</topic><topic>Automation</topic><topic>Child</topic><topic>Child, Preschool</topic><topic>Clinical Research Article</topic><topic>Computer Graphics</topic><topic>Humans</topic><topic>Machine Learning</topic><topic>Medicine</topic><topic>Medicine &amp; Public Health</topic><topic>Observer Variation</topic><topic>Pattern Recognition, Automated</topic><topic>Pediatric Surgery</topic><topic>Pediatrics</topic><topic>Pilot Projects</topic><topic>Plethysmography - instrumentation</topic><topic>Plethysmography - methods</topic><topic>Reproducibility of Results</topic><topic>Respiration</topic><topic>Respiratory Mechanics</topic><topic>Respiratory Rate</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Sleep Apnea Syndromes - diagnosis</topic><topic>Thorax - physiopathology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ratnagiri, Madhavi V.</creatorcontrib><creatorcontrib>Ryan, Lauren</creatorcontrib><creatorcontrib>Strang, Abigail</creatorcontrib><creatorcontrib>Heinle, Robert</creatorcontrib><creatorcontrib>Rahman, Tariq</creatorcontrib><creatorcontrib>Shaffer, Thomas H.</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health &amp; Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Public Health Database</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Pediatric research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ratnagiri, Madhavi V.</au><au>Ryan, Lauren</au><au>Strang, Abigail</au><au>Heinle, Robert</au><au>Rahman, Tariq</au><au>Shaffer, Thomas H.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning for automatic identification of thoracoabdominal asynchrony in children</atitle><jtitle>Pediatric research</jtitle><stitle>Pediatr Res</stitle><addtitle>Pediatr Res</addtitle><date>2021-04-01</date><risdate>2021</risdate><volume>89</volume><issue>5</issue><spage>1232</spage><epage>1238</epage><pages>1232-1238</pages><issn>0031-3998</issn><eissn>1530-0447</eissn><abstract>Background The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection). Methods To assess synchrony between the thorax and abdomen, the movements of the two compartments during quiet breathing were measured using pneu RIP. Fifty-one recordings were obtained: 20 were used to train a machine-learning (ML) model with elastic-net regularization, and 31 were used to test the model’s performance. Two feature sets were explored: (1) phase difference ( ɸ ) between the thoracic and abdominal signals and (2) inverse cumulative percentage (ICP), which is an alternate measure of data distribution. To compute accuracy of training, the model outcomes were compared with five experts’ assessments. Results Accuracies of 61.3% and 90.3% were obtained using ɸ and ICP features, respectively. The inter-rater reliability (i.r.r.) of the assessments of experts was 0.402 and 0.684 when they used ɸ and ICP to identify TAA, respectively. Conclusions With this pilot study, we show the efficacy of the ICP feature and ML in developing an accurate automated approach to identifying TAA that reduces time and effort for diagnosis. ICP also helped improve consensus among experts. Impact Our article presents an automated approach to identifying thoracic abdominal asynchrony using machine learning and the pneu RIP device. It also shows how a modified statistical measure of cumulative frequency can be used to visualize the progression of the pulmonary functionality along time. The pulmonary testing method we developed gives patients and doctors a noninvasive and easy to administer and diagnose approach. It can be administered remotely, and alerts can be transmitted to the physician. Further, the test can also be used to monitor and assess pulmonary function continuously for prolonged periods, if needed.</abstract><cop>New York</cop><pub>Nature Publishing Group US</pub><pmid>32620007</pmid><doi>10.1038/s41390-020-1032-1</doi><tpages>7</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0031-3998
ispartof Pediatric research, 2021-04, Vol.89 (5), p.1232-1238
issn 0031-3998
1530-0447
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10843835
source MEDLINE; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection
subjects Abdomen
Abdomen - physiopathology
Adolescent
Algorithms
Automation
Child
Child, Preschool
Clinical Research Article
Computer Graphics
Humans
Machine Learning
Medicine
Medicine & Public Health
Observer Variation
Pattern Recognition, Automated
Pediatric Surgery
Pediatrics
Pilot Projects
Plethysmography - instrumentation
Plethysmography - methods
Reproducibility of Results
Respiration
Respiratory Mechanics
Respiratory Rate
Signal Processing, Computer-Assisted
Sleep Apnea Syndromes - diagnosis
Thorax - physiopathology
title Machine learning for automatic identification of thoracoabdominal asynchrony in children
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T21%3A59%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20learning%20for%20automatic%20identification%20of%20thoracoabdominal%20asynchrony%20in%20children&rft.jtitle=Pediatric%20research&rft.au=Ratnagiri,%20Madhavi%20V.&rft.date=2021-04-01&rft.volume=89&rft.issue=5&rft.spage=1232&rft.epage=1238&rft.pages=1232-1238&rft.issn=0031-3998&rft.eissn=1530-0447&rft_id=info:doi/10.1038/s41390-020-1032-1&rft_dat=%3Cproquest_pubme%3E2526477800%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2526477800&rft_id=info:pmid/32620007&rfr_iscdi=true