Artificial neural network for risk assessment in preterm neonates
AIM To predict the individual neonatal mortality risk of preterm infants using an artificial neural network “trained” on admission data. METHODS A total of 890 preterm neonates (
Gespeichert in:
| Veröffentlicht in: | Archives of disease in childhood. Fetal and neonatal edition 1998-09, Vol.79 (2), p.F129-F134 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | F134 |
|---|---|
| container_issue | 2 |
| container_start_page | F129 |
| container_title | Archives of disease in childhood. Fetal and neonatal edition |
| container_volume | 79 |
| creator | Zernikow, B Holtmannspoetter, K Michel, E Pielemeier, W Hornschuh, F Westermann, A Hennecke, K H |
| description | AIM To predict the individual neonatal mortality risk of preterm infants using an artificial neural network “trained” on admission data. METHODS A total of 890 preterm neonates ( |
| doi_str_mv | 10.1136/fn.79.2.F129 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_1720838</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>4021324411</sourcerecordid><originalsourceid>FETCH-LOGICAL-b506t-93eddc665aa4a6338c9d3fbd858304de56340c6580ab95ef4b9a6b594db9381a3</originalsourceid><addsrcrecordid>eNp9kUuLFDEURoMo4zi6cysUKLqx2jwqr43QFI4PBt2Mugy3UommuyrVk1T5-Pem7aZRF67uhe_wcS4XoYcErwhh4oWPK6lXdHVJqL6FzkkjVE0xp7fLzriuqdbqLrqX8wZjTKSUZ-hMK6pkg8_Rep3m4IMNMFTRLen3mL9PaVv5KVUp5G0FObucRxfnKsRql9zs0liwKcLs8n10x8OQ3YPjvEAfL19dt2_qqw-v37brq7rjWMy1Zq7vrRAcoAHBmLK6Z77rFVcMN73jgjXYCq4wdJo733QaRMd103eaKQLsAr089O6WbnS9LTrF1uxSGCH9NBME83cSw1fzZfpmiKRYMVUKnh4L0nSzuDybMWTrhgHKKUs2EmMpOeEFfPwPuJmWFMtxpUsVSGohC_X8QNk05ZycP6kQbPaPMT4aqQ01-8cU_NGf-if4-ImSPznmkC0MPkG0IZ8wygok9zX1AQt5dj9OMaStKU6Sm_efWiOuSfuOqc-mLfyzA9-Nm_8L_gKBDbIZ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1780777967</pqid></control><display><type>article</type><title>Artificial neural network for risk assessment in preterm neonates</title><source>MEDLINE</source><source>PubMed Central</source><source>Alma/SFX Local Collection</source><creator>Zernikow, B ; Holtmannspoetter, K ; Michel, E ; Pielemeier, W ; Hornschuh, F ; Westermann, A ; Hennecke, K H</creator><creatorcontrib>Zernikow, B ; Holtmannspoetter, K ; Michel, E ; Pielemeier, W ; Hornschuh, F ; Westermann, A ; Hennecke, K H</creatorcontrib><description>AIM To predict the individual neonatal mortality risk of preterm infants using an artificial neural network “trained” on admission data. METHODS A total of 890 preterm neonates (<32 weeks gestational age and/or <1500 g birthweight) were enrolled in our retrospective study. The neural network trained on infants born between 1990 and 1993. The predictive value was tested on infants born in the successive three years. RESULTS The artificial neural network performed significantly better than a logistic regression model (area under the receiver operator curve 0.95 vs 0.92). Survival was associated with high morbidity if the predicted mortality risk was greater than 0.50. There were no preterm infants with a predicted mortality risk of greater than 0.80. The mortality risks of two non-survivors with birthweights >2000 g and severe congenital disease had largely been underestimated. CONCLUSION An artificial neural network trained on admission data can accurately predict the mortality risk for most preterm infants. However, the significant number of prediction failures renders it unsuitable for individual treatment decisions.</description><identifier>ISSN: 1359-2998</identifier><identifier>EISSN: 1468-2052</identifier><identifier>DOI: 10.1136/fn.79.2.F129</identifier><identifier>PMID: 9828740</identifier><language>eng</language><publisher>London: BMJ Publishing Group Ltd and Royal College of Paediatrics and Child Health</publisher><subject>Accuracy ; Area Under Curve ; artificial neural network ; Biological and medical sciences ; Birth weight ; Body temperature ; Computerized, statistical medical data processing and models in biomedicine ; Female ; Health risks ; Humans ; Infant Mortality ; Infant, Newborn ; Infant, Premature ; Infant, Very Low Birth Weight ; Infants ; Intensive care ; Logistic Models ; Logistics ; Male ; Medical management aid. Diagnosis aid ; Medical sciences ; Morbidity ; Mortality ; Mortality risk ; Neonates ; Neural Networks (Computer) ; Original ; Physiology ; prediction ; Quality ; Regression analysis ; Retrospective Studies ; Risk Assessment ; Sensitivity and Specificity ; Software ; Variables</subject><ispartof>Archives of disease in childhood. Fetal and neonatal edition, 1998-09, Vol.79 (2), p.F129-F134</ispartof><rights>Royal College of Paediatrics and Child Health</rights><rights>1998 INIST-CNRS</rights><rights>Copyright: 1998 Royal College of Paediatrics and Child Health</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-b506t-93eddc665aa4a6338c9d3fbd858304de56340c6580ab95ef4b9a6b594db9381a3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC1720838/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC1720838/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,723,776,780,881,27903,27904,53770,53772</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2374079$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/9828740$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zernikow, B</creatorcontrib><creatorcontrib>Holtmannspoetter, K</creatorcontrib><creatorcontrib>Michel, E</creatorcontrib><creatorcontrib>Pielemeier, W</creatorcontrib><creatorcontrib>Hornschuh, F</creatorcontrib><creatorcontrib>Westermann, A</creatorcontrib><creatorcontrib>Hennecke, K H</creatorcontrib><title>Artificial neural network for risk assessment in preterm neonates</title><title>Archives of disease in childhood. Fetal and neonatal edition</title><addtitle>Arch Dis Child Fetal Neonatal Ed</addtitle><description>AIM To predict the individual neonatal mortality risk of preterm infants using an artificial neural network “trained” on admission data. METHODS A total of 890 preterm neonates (<32 weeks gestational age and/or <1500 g birthweight) were enrolled in our retrospective study. The neural network trained on infants born between 1990 and 1993. The predictive value was tested on infants born in the successive three years. RESULTS The artificial neural network performed significantly better than a logistic regression model (area under the receiver operator curve 0.95 vs 0.92). Survival was associated with high morbidity if the predicted mortality risk was greater than 0.50. There were no preterm infants with a predicted mortality risk of greater than 0.80. The mortality risks of two non-survivors with birthweights >2000 g and severe congenital disease had largely been underestimated. CONCLUSION An artificial neural network trained on admission data can accurately predict the mortality risk for most preterm infants. However, the significant number of prediction failures renders it unsuitable for individual treatment decisions.</description><subject>Accuracy</subject><subject>Area Under Curve</subject><subject>artificial neural network</subject><subject>Biological and medical sciences</subject><subject>Birth weight</subject><subject>Body temperature</subject><subject>Computerized, statistical medical data processing and models in biomedicine</subject><subject>Female</subject><subject>Health risks</subject><subject>Humans</subject><subject>Infant Mortality</subject><subject>Infant, Newborn</subject><subject>Infant, Premature</subject><subject>Infant, Very Low Birth Weight</subject><subject>Infants</subject><subject>Intensive care</subject><subject>Logistic Models</subject><subject>Logistics</subject><subject>Male</subject><subject>Medical management aid. Diagnosis aid</subject><subject>Medical sciences</subject><subject>Morbidity</subject><subject>Mortality</subject><subject>Mortality risk</subject><subject>Neonates</subject><subject>Neural Networks (Computer)</subject><subject>Original</subject><subject>Physiology</subject><subject>prediction</subject><subject>Quality</subject><subject>Regression analysis</subject><subject>Retrospective Studies</subject><subject>Risk Assessment</subject><subject>Sensitivity and Specificity</subject><subject>Software</subject><subject>Variables</subject><issn>1359-2998</issn><issn>1468-2052</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1998</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNp9kUuLFDEURoMo4zi6cysUKLqx2jwqr43QFI4PBt2Mugy3UommuyrVk1T5-Pem7aZRF67uhe_wcS4XoYcErwhh4oWPK6lXdHVJqL6FzkkjVE0xp7fLzriuqdbqLrqX8wZjTKSUZ-hMK6pkg8_Rep3m4IMNMFTRLen3mL9PaVv5KVUp5G0FObucRxfnKsRql9zs0liwKcLs8n10x8OQ3YPjvEAfL19dt2_qqw-v37brq7rjWMy1Zq7vrRAcoAHBmLK6Z77rFVcMN73jgjXYCq4wdJo733QaRMd103eaKQLsAr089O6WbnS9LTrF1uxSGCH9NBME83cSw1fzZfpmiKRYMVUKnh4L0nSzuDybMWTrhgHKKUs2EmMpOeEFfPwPuJmWFMtxpUsVSGohC_X8QNk05ZycP6kQbPaPMT4aqQ01-8cU_NGf-if4-ImSPznmkC0MPkG0IZ8wygok9zX1AQt5dj9OMaStKU6Sm_efWiOuSfuOqc-mLfyzA9-Nm_8L_gKBDbIZ</recordid><startdate>19980901</startdate><enddate>19980901</enddate><creator>Zernikow, B</creator><creator>Holtmannspoetter, K</creator><creator>Michel, E</creator><creator>Pielemeier, W</creator><creator>Hornschuh, F</creator><creator>Westermann, A</creator><creator>Hennecke, K H</creator><general>BMJ Publishing Group Ltd and Royal College of Paediatrics and Child Health</general><general>BMJ</general><general>BMJ Publishing Group LTD</general><general>BMJ Group</general><scope>BSCLL</scope><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>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AEUYN</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BTHHO</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>7X8</scope><scope>5PM</scope></search><sort><creationdate>19980901</creationdate><title>Artificial neural network for risk assessment in preterm neonates</title><author>Zernikow, B ; Holtmannspoetter, K ; Michel, E ; Pielemeier, W ; Hornschuh, F ; Westermann, A ; Hennecke, K H</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-b506t-93eddc665aa4a6338c9d3fbd858304de56340c6580ab95ef4b9a6b594db9381a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1998</creationdate><topic>Accuracy</topic><topic>Area Under Curve</topic><topic>artificial neural network</topic><topic>Biological and medical sciences</topic><topic>Birth weight</topic><topic>Body temperature</topic><topic>Computerized, statistical medical data processing and models in biomedicine</topic><topic>Female</topic><topic>Health risks</topic><topic>Humans</topic><topic>Infant Mortality</topic><topic>Infant, Newborn</topic><topic>Infant, Premature</topic><topic>Infant, Very Low Birth Weight</topic><topic>Infants</topic><topic>Intensive care</topic><topic>Logistic Models</topic><topic>Logistics</topic><topic>Male</topic><topic>Medical management aid. Diagnosis aid</topic><topic>Medical sciences</topic><topic>Morbidity</topic><topic>Mortality</topic><topic>Mortality risk</topic><topic>Neonates</topic><topic>Neural Networks (Computer)</topic><topic>Original</topic><topic>Physiology</topic><topic>prediction</topic><topic>Quality</topic><topic>Regression analysis</topic><topic>Retrospective Studies</topic><topic>Risk Assessment</topic><topic>Sensitivity and Specificity</topic><topic>Software</topic><topic>Variables</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zernikow, B</creatorcontrib><creatorcontrib>Holtmannspoetter, K</creatorcontrib><creatorcontrib>Michel, E</creatorcontrib><creatorcontrib>Pielemeier, W</creatorcontrib><creatorcontrib>Hornschuh, F</creatorcontrib><creatorcontrib>Westermann, A</creatorcontrib><creatorcontrib>Hennecke, K H</creatorcontrib><collection>Istex</collection><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>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</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 One Sustainability</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>BMJ Journals</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & 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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Archives of disease in childhood. Fetal and neonatal edition</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zernikow, B</au><au>Holtmannspoetter, K</au><au>Michel, E</au><au>Pielemeier, W</au><au>Hornschuh, F</au><au>Westermann, A</au><au>Hennecke, K H</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial neural network for risk assessment in preterm neonates</atitle><jtitle>Archives of disease in childhood. Fetal and neonatal edition</jtitle><addtitle>Arch Dis Child Fetal Neonatal Ed</addtitle><date>1998-09-01</date><risdate>1998</risdate><volume>79</volume><issue>2</issue><spage>F129</spage><epage>F134</epage><pages>F129-F134</pages><issn>1359-2998</issn><eissn>1468-2052</eissn><abstract>AIM To predict the individual neonatal mortality risk of preterm infants using an artificial neural network “trained” on admission data. METHODS A total of 890 preterm neonates (<32 weeks gestational age and/or <1500 g birthweight) were enrolled in our retrospective study. The neural network trained on infants born between 1990 and 1993. The predictive value was tested on infants born in the successive three years. RESULTS The artificial neural network performed significantly better than a logistic regression model (area under the receiver operator curve 0.95 vs 0.92). Survival was associated with high morbidity if the predicted mortality risk was greater than 0.50. There were no preterm infants with a predicted mortality risk of greater than 0.80. The mortality risks of two non-survivors with birthweights >2000 g and severe congenital disease had largely been underestimated. CONCLUSION An artificial neural network trained on admission data can accurately predict the mortality risk for most preterm infants. However, the significant number of prediction failures renders it unsuitable for individual treatment decisions.</abstract><cop>London</cop><pub>BMJ Publishing Group Ltd and Royal College of Paediatrics and Child Health</pub><pmid>9828740</pmid><doi>10.1136/fn.79.2.F129</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1359-2998 |
| ispartof | Archives of disease in childhood. Fetal and neonatal edition, 1998-09, Vol.79 (2), p.F129-F134 |
| issn | 1359-2998 1468-2052 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_1720838 |
| source | MEDLINE; PubMed Central; Alma/SFX Local Collection |
| subjects | Accuracy Area Under Curve artificial neural network Biological and medical sciences Birth weight Body temperature Computerized, statistical medical data processing and models in biomedicine Female Health risks Humans Infant Mortality Infant, Newborn Infant, Premature Infant, Very Low Birth Weight Infants Intensive care Logistic Models Logistics Male Medical management aid. Diagnosis aid Medical sciences Morbidity Mortality Mortality risk Neonates Neural Networks (Computer) Original Physiology prediction Quality Regression analysis Retrospective Studies Risk Assessment Sensitivity and Specificity Software Variables |
| title | Artificial neural network for risk assessment in preterm neonates |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T00%3A44%3A30IST&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=Artificial%20neural%20network%20for%20risk%20assessment%20in%20preterm%20neonates&rft.jtitle=Archives%20of%20disease%20in%20childhood.%20Fetal%20and%20neonatal%20edition&rft.au=Zernikow,%20B&rft.date=1998-09-01&rft.volume=79&rft.issue=2&rft.spage=F129&rft.epage=F134&rft.pages=F129-F134&rft.issn=1359-2998&rft.eissn=1468-2052&rft_id=info:doi/10.1136/fn.79.2.F129&rft_dat=%3Cproquest_pubme%3E4021324411%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=1780777967&rft_id=info:pmid/9828740&rfr_iscdi=true |