Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance
Abstract Background In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been devel...
Gespeichert in:
Veröffentlicht in: | Early human development 2012-07, Vol.88 (7), p.547-553 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 553 |
---|---|
container_issue | 7 |
container_start_page | 547 |
container_title | Early human development |
container_volume | 88 |
creator | LUKIC, Stevo COJBASIC, Zarko JOVIC, Nebojsa POPOVIC, Mirjana BJELAKOVIC, Bojko DIMITRIJEVIC, Lidija BJELAKOVIC, Ljiljana |
description | Abstract Background In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been developed in many areas of health care research, but there are no published studies considered ANN models for prediction of cerebral palsy (CP) development. Objective To compare the results of an ANN analysis with results of regression analysis, using the same data set and the same clinical and HRV parameters. Methods The study included 35 infants with CCD and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24 h electrocardiography recordings. Clinical parameters and selected time domain HRV parameters are used to predict CP by logistic regression, and then an ANN analysis was applied to the same data set. Input variables were age, gender, postural responses, heart rate parameters (minimum, maximum and average), and time domain parameters of HRV (SDNN, SDANN and RMSSD). For each of one the pairs of ANN and clinical predictors, the area under the receiver operating characteristic (ROC) curves with test accuracy parameters were calculated and compared. Results In the observed dataset, ANN model overall correctly classified all infants, compared with 86.11% correct classification for the logistic regression model, and compared with 67.65% and 77.14% for SDANN and SDNN respectively. Conclusions ANN model, based on clinical and HRV data can predict development of CP in patients with CCD with accuracy greater than 90%. Our results strongly indicate that a well-validated ANN may have a role in the clinical prediction of CP in infants with CCD. |
doi_str_mv | 10.1016/j.earlhumdev.2012.01.001 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1399915267</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0378378212000023</els_id><sourcerecordid>1018635785</sourcerecordid><originalsourceid>FETCH-LOGICAL-c492t-be1230cf509102423eff084ed7b28115342dd32ea6eaa67638ba566ca70e846e3</originalsourceid><addsrcrecordid>eNqNkk1v1DAQhi0EokvhL6BckLgkjO3EcS5IpeJLqsQBOFuOPVG9zdqL7bTaf1-nu1CJC0i25jDPOzOadwipKDQUqHi3bVDH-XrZWbxtGFDWAG0A6BOyobJntWCcPSUb4L2sy2dn5EVKWwDo5ADPyRljTFLo-g3xFzG7yRmn58rjEh9CvgvxJlWjTmirfUTrTHbBV2GqDEYcV2qv53SonC9v0j6n6s7l65L2ec2aEKJ1Xj_IrEt5iaP2Bl-SZ1MR4qtTPCc_P338cfmlvvr2-evlxVVt2oHlekTKOJipg4ECaxnHaQLZou3HMjjteMus5Qy1QK1FL7gcdSeE0T2gbAXyc_L2WHcfw68FU1Y7lwzOs_YYlqQoH4aBdkz0_0aBSsG7XnYFlUfUxJBSxEnto9vpeCjQygm1VY_GqNUYBVQVY4r09anLMu7Q_hH-dqIAb06ATkbPUyzrcumR6wbBBEDhPhw5LOu7dRhVMg7Laq2LaLKywf3PNO__KmJm513pe4MHTNuwRF_sUVSlolHf10Na74iyckPAOL8HUTrHNg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1018635785</pqid></control><display><type>article</type><title>Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance</title><source>MEDLINE</source><source>Access via ScienceDirect (Elsevier)</source><creator>LUKIC, Stevo ; COJBASIC, Zarko ; JOVIC, Nebojsa ; POPOVIC, Mirjana ; BJELAKOVIC, Bojko ; DIMITRIJEVIC, Lidija ; BJELAKOVIC, Ljiljana</creator><creatorcontrib>LUKIC, Stevo ; COJBASIC, Zarko ; JOVIC, Nebojsa ; POPOVIC, Mirjana ; BJELAKOVIC, Bojko ; DIMITRIJEVIC, Lidija ; BJELAKOVIC, Ljiljana</creatorcontrib><description>Abstract Background In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been developed in many areas of health care research, but there are no published studies considered ANN models for prediction of cerebral palsy (CP) development. Objective To compare the results of an ANN analysis with results of regression analysis, using the same data set and the same clinical and HRV parameters. Methods The study included 35 infants with CCD and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24 h electrocardiography recordings. Clinical parameters and selected time domain HRV parameters are used to predict CP by logistic regression, and then an ANN analysis was applied to the same data set. Input variables were age, gender, postural responses, heart rate parameters (minimum, maximum and average), and time domain parameters of HRV (SDNN, SDANN and RMSSD). For each of one the pairs of ANN and clinical predictors, the area under the receiver operating characteristic (ROC) curves with test accuracy parameters were calculated and compared. Results In the observed dataset, ANN model overall correctly classified all infants, compared with 86.11% correct classification for the logistic regression model, and compared with 67.65% and 77.14% for SDANN and SDNN respectively. Conclusions ANN model, based on clinical and HRV data can predict development of CP in patients with CCD with accuracy greater than 90%. Our results strongly indicate that a well-validated ANN may have a role in the clinical prediction of CP in infants with CCD.</description><identifier>ISSN: 0378-3782</identifier><identifier>EISSN: 1872-6232</identifier><identifier>DOI: 10.1016/j.earlhumdev.2012.01.001</identifier><identifier>PMID: 22281057</identifier><identifier>CODEN: EHDEDN</identifier><language>eng</language><publisher>Amsterdam: Elsevier Ireland Ltd</publisher><subject>Advanced Basic Science ; Artificial neural network ; Ataxia - complications ; Ataxia - diagnosis ; Biological and medical sciences ; Case-Control Studies ; Central coordination disturbance ; Cerebral Palsy - complications ; Cerebral Palsy - diagnosis ; Electrocardiography - methods ; Embryology: invertebrates and vertebrates. Teratology ; Female ; Forecasting - methods ; Fundamental and applied biological sciences. Psychology ; Heart rate variability ; Humans ; Infant ; Infant, Newborn ; Male ; Models, Biological ; Neonatal and Perinatal Medicine ; Neural Networks (Computer) ; Permanent motor disability ; Prognosis ; ROC Curve</subject><ispartof>Early human development, 2012-07, Vol.88 (7), p.547-553</ispartof><rights>Elsevier Ltd</rights><rights>2012 Elsevier Ltd</rights><rights>2015 INIST-CNRS</rights><rights>Copyright © 2012 Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c492t-be1230cf509102423eff084ed7b28115342dd32ea6eaa67638ba566ca70e846e3</citedby><cites>FETCH-LOGICAL-c492t-be1230cf509102423eff084ed7b28115342dd32ea6eaa67638ba566ca70e846e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.earlhumdev.2012.01.001$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=25962600$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/22281057$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>LUKIC, Stevo</creatorcontrib><creatorcontrib>COJBASIC, Zarko</creatorcontrib><creatorcontrib>JOVIC, Nebojsa</creatorcontrib><creatorcontrib>POPOVIC, Mirjana</creatorcontrib><creatorcontrib>BJELAKOVIC, Bojko</creatorcontrib><creatorcontrib>DIMITRIJEVIC, Lidija</creatorcontrib><creatorcontrib>BJELAKOVIC, Ljiljana</creatorcontrib><title>Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance</title><title>Early human development</title><addtitle>Early Hum Dev</addtitle><description>Abstract Background In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been developed in many areas of health care research, but there are no published studies considered ANN models for prediction of cerebral palsy (CP) development. Objective To compare the results of an ANN analysis with results of regression analysis, using the same data set and the same clinical and HRV parameters. Methods The study included 35 infants with CCD and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24 h electrocardiography recordings. Clinical parameters and selected time domain HRV parameters are used to predict CP by logistic regression, and then an ANN analysis was applied to the same data set. Input variables were age, gender, postural responses, heart rate parameters (minimum, maximum and average), and time domain parameters of HRV (SDNN, SDANN and RMSSD). For each of one the pairs of ANN and clinical predictors, the area under the receiver operating characteristic (ROC) curves with test accuracy parameters were calculated and compared. Results In the observed dataset, ANN model overall correctly classified all infants, compared with 86.11% correct classification for the logistic regression model, and compared with 67.65% and 77.14% for SDANN and SDNN respectively. Conclusions ANN model, based on clinical and HRV data can predict development of CP in patients with CCD with accuracy greater than 90%. Our results strongly indicate that a well-validated ANN may have a role in the clinical prediction of CP in infants with CCD.</description><subject>Advanced Basic Science</subject><subject>Artificial neural network</subject><subject>Ataxia - complications</subject><subject>Ataxia - diagnosis</subject><subject>Biological and medical sciences</subject><subject>Case-Control Studies</subject><subject>Central coordination disturbance</subject><subject>Cerebral Palsy - complications</subject><subject>Cerebral Palsy - diagnosis</subject><subject>Electrocardiography - methods</subject><subject>Embryology: invertebrates and vertebrates. Teratology</subject><subject>Female</subject><subject>Forecasting - methods</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>Heart rate variability</subject><subject>Humans</subject><subject>Infant</subject><subject>Infant, Newborn</subject><subject>Male</subject><subject>Models, Biological</subject><subject>Neonatal and Perinatal Medicine</subject><subject>Neural Networks (Computer)</subject><subject>Permanent motor disability</subject><subject>Prognosis</subject><subject>ROC Curve</subject><issn>0378-3782</issn><issn>1872-6232</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNkk1v1DAQhi0EokvhL6BckLgkjO3EcS5IpeJLqsQBOFuOPVG9zdqL7bTaf1-nu1CJC0i25jDPOzOadwipKDQUqHi3bVDH-XrZWbxtGFDWAG0A6BOyobJntWCcPSUb4L2sy2dn5EVKWwDo5ADPyRljTFLo-g3xFzG7yRmn58rjEh9CvgvxJlWjTmirfUTrTHbBV2GqDEYcV2qv53SonC9v0j6n6s7l65L2ec2aEKJ1Xj_IrEt5iaP2Bl-SZ1MR4qtTPCc_P338cfmlvvr2-evlxVVt2oHlekTKOJipg4ECaxnHaQLZou3HMjjteMus5Qy1QK1FL7gcdSeE0T2gbAXyc_L2WHcfw68FU1Y7lwzOs_YYlqQoH4aBdkz0_0aBSsG7XnYFlUfUxJBSxEnto9vpeCjQygm1VY_GqNUYBVQVY4r09anLMu7Q_hH-dqIAb06ATkbPUyzrcumR6wbBBEDhPhw5LOu7dRhVMg7Laq2LaLKywf3PNO__KmJm513pe4MHTNuwRF_sUVSlolHf10Na74iyckPAOL8HUTrHNg</recordid><startdate>20120701</startdate><enddate>20120701</enddate><creator>LUKIC, Stevo</creator><creator>COJBASIC, Zarko</creator><creator>JOVIC, Nebojsa</creator><creator>POPOVIC, Mirjana</creator><creator>BJELAKOVIC, Bojko</creator><creator>DIMITRIJEVIC, Lidija</creator><creator>BJELAKOVIC, Ljiljana</creator><general>Elsevier Ireland Ltd</general><general>Elsevier</general><scope>IQODW</scope><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>7X8</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope></search><sort><creationdate>20120701</creationdate><title>Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance</title><author>LUKIC, Stevo ; COJBASIC, Zarko ; JOVIC, Nebojsa ; POPOVIC, Mirjana ; BJELAKOVIC, Bojko ; DIMITRIJEVIC, Lidija ; BJELAKOVIC, Ljiljana</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c492t-be1230cf509102423eff084ed7b28115342dd32ea6eaa67638ba566ca70e846e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Advanced Basic Science</topic><topic>Artificial neural network</topic><topic>Ataxia - complications</topic><topic>Ataxia - diagnosis</topic><topic>Biological and medical sciences</topic><topic>Case-Control Studies</topic><topic>Central coordination disturbance</topic><topic>Cerebral Palsy - complications</topic><topic>Cerebral Palsy - diagnosis</topic><topic>Electrocardiography - methods</topic><topic>Embryology: invertebrates and vertebrates. Teratology</topic><topic>Female</topic><topic>Forecasting - methods</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>Heart rate variability</topic><topic>Humans</topic><topic>Infant</topic><topic>Infant, Newborn</topic><topic>Male</topic><topic>Models, Biological</topic><topic>Neonatal and Perinatal Medicine</topic><topic>Neural Networks (Computer)</topic><topic>Permanent motor disability</topic><topic>Prognosis</topic><topic>ROC Curve</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>LUKIC, Stevo</creatorcontrib><creatorcontrib>COJBASIC, Zarko</creatorcontrib><creatorcontrib>JOVIC, Nebojsa</creatorcontrib><creatorcontrib>POPOVIC, Mirjana</creatorcontrib><creatorcontrib>BJELAKOVIC, Bojko</creatorcontrib><creatorcontrib>DIMITRIJEVIC, Lidija</creatorcontrib><creatorcontrib>BJELAKOVIC, Ljiljana</creatorcontrib><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Early human development</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>LUKIC, Stevo</au><au>COJBASIC, Zarko</au><au>JOVIC, Nebojsa</au><au>POPOVIC, Mirjana</au><au>BJELAKOVIC, Bojko</au><au>DIMITRIJEVIC, Lidija</au><au>BJELAKOVIC, Ljiljana</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance</atitle><jtitle>Early human development</jtitle><addtitle>Early Hum Dev</addtitle><date>2012-07-01</date><risdate>2012</risdate><volume>88</volume><issue>7</issue><spage>547</spage><epage>553</epage><pages>547-553</pages><issn>0378-3782</issn><eissn>1872-6232</eissn><coden>EHDEDN</coden><abstract>Abstract Background In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been developed in many areas of health care research, but there are no published studies considered ANN models for prediction of cerebral palsy (CP) development. Objective To compare the results of an ANN analysis with results of regression analysis, using the same data set and the same clinical and HRV parameters. Methods The study included 35 infants with CCD and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24 h electrocardiography recordings. Clinical parameters and selected time domain HRV parameters are used to predict CP by logistic regression, and then an ANN analysis was applied to the same data set. Input variables were age, gender, postural responses, heart rate parameters (minimum, maximum and average), and time domain parameters of HRV (SDNN, SDANN and RMSSD). For each of one the pairs of ANN and clinical predictors, the area under the receiver operating characteristic (ROC) curves with test accuracy parameters were calculated and compared. Results In the observed dataset, ANN model overall correctly classified all infants, compared with 86.11% correct classification for the logistic regression model, and compared with 67.65% and 77.14% for SDANN and SDNN respectively. Conclusions ANN model, based on clinical and HRV data can predict development of CP in patients with CCD with accuracy greater than 90%. Our results strongly indicate that a well-validated ANN may have a role in the clinical prediction of CP in infants with CCD.</abstract><cop>Amsterdam</cop><pub>Elsevier Ireland Ltd</pub><pmid>22281057</pmid><doi>10.1016/j.earlhumdev.2012.01.001</doi><tpages>7</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0378-3782 |
ispartof | Early human development, 2012-07, Vol.88 (7), p.547-553 |
issn | 0378-3782 1872-6232 |
language | eng |
recordid | cdi_proquest_miscellaneous_1399915267 |
source | MEDLINE; Access via ScienceDirect (Elsevier) |
subjects | Advanced Basic Science Artificial neural network Ataxia - complications Ataxia - diagnosis Biological and medical sciences Case-Control Studies Central coordination disturbance Cerebral Palsy - complications Cerebral Palsy - diagnosis Electrocardiography - methods Embryology: invertebrates and vertebrates. Teratology Female Forecasting - methods Fundamental and applied biological sciences. Psychology Heart rate variability Humans Infant Infant, Newborn Male Models, Biological Neonatal and Perinatal Medicine Neural Networks (Computer) Permanent motor disability Prognosis ROC Curve |
title | Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T22%3A33%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Artificial%20neural%20networks%20based%20prediction%20of%20cerebral%20palsy%20in%20infants%20with%20central%20coordination%20disturbance&rft.jtitle=Early%20human%20development&rft.au=LUKIC,%20Stevo&rft.date=2012-07-01&rft.volume=88&rft.issue=7&rft.spage=547&rft.epage=553&rft.pages=547-553&rft.issn=0378-3782&rft.eissn=1872-6232&rft.coden=EHDEDN&rft_id=info:doi/10.1016/j.earlhumdev.2012.01.001&rft_dat=%3Cproquest_cross%3E1018635785%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1018635785&rft_id=info:pmid/22281057&rft_els_id=S0378378212000023&rfr_iscdi=true |