Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study
Background To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models. Methods This study retrospectively compared LR and ANN models based on initial clinical data for 22...
Gespeichert in:
| Veröffentlicht in: | Journal of gastrointestinal surgery 2012-11, Vol.16 (11), p.2126-2131 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2131 |
|---|---|
| container_issue | 11 |
| container_start_page | 2126 |
| container_title | Journal of gastrointestinal surgery |
| container_volume | 16 |
| creator | Shi, Hon-Yi Lee, King-Teh Wang, Jhi-Joung Sun, Ding-Ping Lee, Hao-Hsien Chiu, Chong-Chi |
| description | Background
To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models.
Methods
This study retrospectively compared LR and ANN models based on initial clinical data for 22,926 HCC surgery patients from 1998 to 2009. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the importance of variables.
Results
Compared to the LR models, the ANN models had a better accuracy rate in 96.57 % of cases, a better Hosmer–Lemeshow statistic in 0.34 of cases, and a better receiver operating characteristic curves in 88.51 % of cases. Surgeon volume was the most influential (sensitive) parameter affecting 5-year mortality followed by hospital volume and Charlson co-morbidity index.
Conclusions
In comparison with the conventional LR model, the ANN model in this study was more accurate in predicting 5-year mortality. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data. |
| doi_str_mv | 10.1007/s11605-012-1986-3 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1151700620</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1151700620</sourcerecordid><originalsourceid>FETCH-LOGICAL-c405t-fceaf38e2c968cb756cf39677b6ebb549b5e6b35b0593583537d50b420ee706a3</originalsourceid><addsrcrecordid>eNp1kU2LFDEQhoMo7of-AC8S8OIlmo9O0vE2DOoK6yqsgp5Ckq5esvZ0xiTNMhd_-2Z2VhFB6lAF9dRbRb0IPWP0FaNUvy6MKSoJZZww0ysiHqBj1mtBOsXVw1ZTwwiX8tsROinlmlKmKesfoyPOe72PY_RrlWscY4huwhew5LtUb1L-gT-mASY8pow_ZxhiqHG-wpJ8B5dbL1c3xbrDq7FCxpdLvoK8u6PPYOtqCjBNy9TQtcshzmnj3uAVvnA1pvkmDoAv6zLsnqBHo5sKPL3Pp-jru7df1mfk_NP7D-vVOQkdlZWMAdwoeuDBqD54LVUYhVFaewXey854CcoL6ak0QvZCCj1I6jtOATRVTpyilwfdbU4_FyjVbmLZn-hmSEuxjMn2G6o4beiLf9DrtOS5XdeozhjW1plGsQMVciolw2i3OW5c3llG7d4cezDHNnPs3hwr2szze-XFb2D4M_HbjQbwA1Baa24P_Wv1f1VvAQ0NmkM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1149915499</pqid></control><display><type>article</type><title>Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study</title><source>MEDLINE</source><source>SpringerLink Journals</source><creator>Shi, Hon-Yi ; Lee, King-Teh ; Wang, Jhi-Joung ; Sun, Ding-Ping ; Lee, Hao-Hsien ; Chiu, Chong-Chi</creator><creatorcontrib>Shi, Hon-Yi ; Lee, King-Teh ; Wang, Jhi-Joung ; Sun, Ding-Ping ; Lee, Hao-Hsien ; Chiu, Chong-Chi</creatorcontrib><description>Background
To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models.
Methods
This study retrospectively compared LR and ANN models based on initial clinical data for 22,926 HCC surgery patients from 1998 to 2009. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the importance of variables.
Results
Compared to the LR models, the ANN models had a better accuracy rate in 96.57 % of cases, a better Hosmer–Lemeshow statistic in 0.34 of cases, and a better receiver operating characteristic curves in 88.51 % of cases. Surgeon volume was the most influential (sensitive) parameter affecting 5-year mortality followed by hospital volume and Charlson co-morbidity index.
Conclusions
In comparison with the conventional LR model, the ANN model in this study was more accurate in predicting 5-year mortality. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.</description><identifier>ISSN: 1091-255X</identifier><identifier>EISSN: 1873-4626</identifier><identifier>DOI: 10.1007/s11605-012-1986-3</identifier><identifier>PMID: 22878787</identifier><language>eng</language><publisher>New York: Springer-Verlag</publisher><subject>Bile ducts ; Carcinoma, Hepatocellular - mortality ; Carcinoma, Hepatocellular - surgery ; Codes ; Data collection ; Feasibility Studies ; Female ; Gastroenterology ; Hepatectomy ; Hospitals ; Humans ; Liver cancer ; Liver Neoplasms - mortality ; Liver Neoplasms - surgery ; Logistic Models ; Male ; Medicine ; Medicine & Public Health ; Middle Aged ; Morbidity ; Mortality ; National health insurance ; Neural networks ; Neural Networks, Computer ; Original Article ; Patients ; Regression analysis ; ROC Curve ; Surgeons ; Surgery ; Tumors</subject><ispartof>Journal of gastrointestinal surgery, 2012-11, Vol.16 (11), p.2126-2131</ispartof><rights>The Society for Surgery of the Alimentary Tract 2012</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c405t-fceaf38e2c968cb756cf39677b6ebb549b5e6b35b0593583537d50b420ee706a3</citedby><cites>FETCH-LOGICAL-c405t-fceaf38e2c968cb756cf39677b6ebb549b5e6b35b0593583537d50b420ee706a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11605-012-1986-3$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11605-012-1986-3$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/22878787$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Shi, Hon-Yi</creatorcontrib><creatorcontrib>Lee, King-Teh</creatorcontrib><creatorcontrib>Wang, Jhi-Joung</creatorcontrib><creatorcontrib>Sun, Ding-Ping</creatorcontrib><creatorcontrib>Lee, Hao-Hsien</creatorcontrib><creatorcontrib>Chiu, Chong-Chi</creatorcontrib><title>Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study</title><title>Journal of gastrointestinal surgery</title><addtitle>J Gastrointest Surg</addtitle><addtitle>J Gastrointest Surg</addtitle><description>Background
To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models.
Methods
This study retrospectively compared LR and ANN models based on initial clinical data for 22,926 HCC surgery patients from 1998 to 2009. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the importance of variables.
Results
Compared to the LR models, the ANN models had a better accuracy rate in 96.57 % of cases, a better Hosmer–Lemeshow statistic in 0.34 of cases, and a better receiver operating characteristic curves in 88.51 % of cases. Surgeon volume was the most influential (sensitive) parameter affecting 5-year mortality followed by hospital volume and Charlson co-morbidity index.
Conclusions
In comparison with the conventional LR model, the ANN model in this study was more accurate in predicting 5-year mortality. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.</description><subject>Bile ducts</subject><subject>Carcinoma, Hepatocellular - mortality</subject><subject>Carcinoma, Hepatocellular - surgery</subject><subject>Codes</subject><subject>Data collection</subject><subject>Feasibility Studies</subject><subject>Female</subject><subject>Gastroenterology</subject><subject>Hepatectomy</subject><subject>Hospitals</subject><subject>Humans</subject><subject>Liver cancer</subject><subject>Liver Neoplasms - mortality</subject><subject>Liver Neoplasms - surgery</subject><subject>Logistic Models</subject><subject>Male</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Middle Aged</subject><subject>Morbidity</subject><subject>Mortality</subject><subject>National health insurance</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Original Article</subject><subject>Patients</subject><subject>Regression analysis</subject><subject>ROC Curve</subject><subject>Surgeons</subject><subject>Surgery</subject><subject>Tumors</subject><issn>1091-255X</issn><issn>1873-4626</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>BENPR</sourceid><recordid>eNp1kU2LFDEQhoMo7of-AC8S8OIlmo9O0vE2DOoK6yqsgp5Ckq5esvZ0xiTNMhd_-2Z2VhFB6lAF9dRbRb0IPWP0FaNUvy6MKSoJZZww0ysiHqBj1mtBOsXVw1ZTwwiX8tsROinlmlKmKesfoyPOe72PY_RrlWscY4huwhew5LtUb1L-gT-mASY8pow_ZxhiqHG-wpJ8B5dbL1c3xbrDq7FCxpdLvoK8u6PPYOtqCjBNy9TQtcshzmnj3uAVvnA1pvkmDoAv6zLsnqBHo5sKPL3Pp-jru7df1mfk_NP7D-vVOQkdlZWMAdwoeuDBqD54LVUYhVFaewXey854CcoL6ak0QvZCCj1I6jtOATRVTpyilwfdbU4_FyjVbmLZn-hmSEuxjMn2G6o4beiLf9DrtOS5XdeozhjW1plGsQMVciolw2i3OW5c3llG7d4cezDHNnPs3hwr2szze-XFb2D4M_HbjQbwA1Baa24P_Wv1f1VvAQ0NmkM</recordid><startdate>20121101</startdate><enddate>20121101</enddate><creator>Shi, Hon-Yi</creator><creator>Lee, King-Teh</creator><creator>Wang, Jhi-Joung</creator><creator>Sun, Ding-Ping</creator><creator>Lee, Hao-Hsien</creator><creator>Chiu, Chong-Chi</creator><general>Springer-Verlag</general><general>Springer Nature B.V</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>7RV</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</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>KB0</scope><scope>M0S</scope><scope>M1P</scope><scope>NAPCQ</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>7X8</scope></search><sort><creationdate>20121101</creationdate><title>Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study</title><author>Shi, Hon-Yi ; Lee, King-Teh ; Wang, Jhi-Joung ; Sun, Ding-Ping ; Lee, Hao-Hsien ; Chiu, Chong-Chi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c405t-fceaf38e2c968cb756cf39677b6ebb549b5e6b35b0593583537d50b420ee706a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Bile ducts</topic><topic>Carcinoma, Hepatocellular - mortality</topic><topic>Carcinoma, Hepatocellular - surgery</topic><topic>Codes</topic><topic>Data collection</topic><topic>Feasibility Studies</topic><topic>Female</topic><topic>Gastroenterology</topic><topic>Hepatectomy</topic><topic>Hospitals</topic><topic>Humans</topic><topic>Liver cancer</topic><topic>Liver Neoplasms - mortality</topic><topic>Liver Neoplasms - surgery</topic><topic>Logistic Models</topic><topic>Male</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Middle Aged</topic><topic>Morbidity</topic><topic>Mortality</topic><topic>National health insurance</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Original Article</topic><topic>Patients</topic><topic>Regression analysis</topic><topic>ROC Curve</topic><topic>Surgeons</topic><topic>Surgery</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shi, Hon-Yi</creatorcontrib><creatorcontrib>Lee, King-Teh</creatorcontrib><creatorcontrib>Wang, Jhi-Joung</creatorcontrib><creatorcontrib>Sun, Ding-Ping</creatorcontrib><creatorcontrib>Lee, Hao-Hsien</creatorcontrib><creatorcontrib>Chiu, Chong-Chi</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>Nursing & Allied Health Database</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</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 & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Nursing & Allied Health Premium</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><jtitle>Journal of gastrointestinal surgery</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shi, Hon-Yi</au><au>Lee, King-Teh</au><au>Wang, Jhi-Joung</au><au>Sun, Ding-Ping</au><au>Lee, Hao-Hsien</au><au>Chiu, Chong-Chi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study</atitle><jtitle>Journal of gastrointestinal surgery</jtitle><stitle>J Gastrointest Surg</stitle><addtitle>J Gastrointest Surg</addtitle><date>2012-11-01</date><risdate>2012</risdate><volume>16</volume><issue>11</issue><spage>2126</spage><epage>2131</epage><pages>2126-2131</pages><issn>1091-255X</issn><eissn>1873-4626</eissn><abstract>Background
To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models.
Methods
This study retrospectively compared LR and ANN models based on initial clinical data for 22,926 HCC surgery patients from 1998 to 2009. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the importance of variables.
Results
Compared to the LR models, the ANN models had a better accuracy rate in 96.57 % of cases, a better Hosmer–Lemeshow statistic in 0.34 of cases, and a better receiver operating characteristic curves in 88.51 % of cases. Surgeon volume was the most influential (sensitive) parameter affecting 5-year mortality followed by hospital volume and Charlson co-morbidity index.
Conclusions
In comparison with the conventional LR model, the ANN model in this study was more accurate in predicting 5-year mortality. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.</abstract><cop>New York</cop><pub>Springer-Verlag</pub><pmid>22878787</pmid><doi>10.1007/s11605-012-1986-3</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1091-255X |
| ispartof | Journal of gastrointestinal surgery, 2012-11, Vol.16 (11), p.2126-2131 |
| issn | 1091-255X 1873-4626 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1151700620 |
| source | MEDLINE; SpringerLink Journals |
| subjects | Bile ducts Carcinoma, Hepatocellular - mortality Carcinoma, Hepatocellular - surgery Codes Data collection Feasibility Studies Female Gastroenterology Hepatectomy Hospitals Humans Liver cancer Liver Neoplasms - mortality Liver Neoplasms - surgery Logistic Models Male Medicine Medicine & Public Health Middle Aged Morbidity Mortality National health insurance Neural networks Neural Networks, Computer Original Article Patients Regression analysis ROC Curve Surgeons Surgery Tumors |
| title | Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T09%3A55%3A00IST&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%20Network%20Model%20for%20Predicting%205-Year%20Mortality%20After%20Surgery%20for%20Hepatocellular%20Carcinoma:%20A%20Nationwide%20Study&rft.jtitle=Journal%20of%20gastrointestinal%20surgery&rft.au=Shi,%20Hon-Yi&rft.date=2012-11-01&rft.volume=16&rft.issue=11&rft.spage=2126&rft.epage=2131&rft.pages=2126-2131&rft.issn=1091-255X&rft.eissn=1873-4626&rft_id=info:doi/10.1007/s11605-012-1986-3&rft_dat=%3Cproquest_cross%3E1151700620%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=1149915499&rft_id=info:pmid/22878787&rfr_iscdi=true |