Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model
This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong. This retrospective analysis included all patients admitted...
Gespeichert in:
| Veröffentlicht in: | Hong Kong Medical Journal 2024-04, Vol.30 (2), p.130-138 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 138 |
|---|---|
| container_issue | 2 |
| container_start_page | 130 |
| container_title | Hong Kong Medical Journal |
| container_volume | 30 |
| creator | Lau, S Shum, H P Chan, C C Y Man, M Y Tang, K B Chan, K K C Leung, A K H Yan, W W |
| description | This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong.
This retrospective analysis included all patients admitted to the intensive care unit of Pamela Youde Nethersole Eastern Hospital from January 2010 to December 2019. The ANN model was constructed using parameters identical to the APACHE IV model. Discrimination performance was assessed using area under the receiver operating characteristic curve (AUROC); calibration performance was evaluated using the Brier score and Hosmer-Lemeshow statistic.
In total, 14 503 patients were included, with 10% in the validation set and 90% in the ANN model development set. The ANN model (AUROC=0.88, 95% confidence interval [CI]=0.86-0.90, Brier score=0.10; P in Hosmer-Lemeshow test=0.37) outperformed the APACHE II model (AUROC=0.85, 95% CI=0.80-0.85, Brier score=0.14; P |
| doi_str_mv | 10.12809/hkmj2210235 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3014008288</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3014008288</sourcerecordid><originalsourceid>FETCH-LOGICAL-c314t-885e1d224e23effacd5581ed6a05e2f30504ea945b9e13aa42f8bcbc55a22cea3</originalsourceid><addsrcrecordid>eNpdkU1v1DAYhC1ERZfCjTOyxIUDAX_EG4dbVfElVWoPcI7eOG-279aJg-2o2l_E36zpFoQ4jTR6NDPSMPZKivdSWdF-uLmd9kpJobR5wjZKqW1lG9E8ZZvi1ZVqhD1lz1PaC6GsacUzdqqtqc1Wtxv26zriQC5TmHkY-U1IC2XwfAqxCOUDhynMO-4iZXLg_YGT93yBTDjnxGnmwBPNO4_cFSfib-s8EXzkLkwLRErHaIiZRnJUwmdc44PkuxBvE4d54D7sKJUKHnEXMaUyqOoh4VCmDOhfsJMRfMKXj3rGfnz-9P3ia3V59eXbxfll5bSsc2WtQTkoVaPSOI7gBmOsxGELwqAatTCiRmhr07coNUCtRtu73hkDSjkEfcbeHnOXGH6umHI3UXLoPcwY1tRpIWshrLK2oG_-Q_dhjXNZ12kplWy0Nk2h3h0pF0NKEcduiTRBPHRSdA8Hdv8cWPDXj6FrP-HwF_7zmL4HbIyatA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3112173357</pqid></control><display><type>article</type><title>Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model</title><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Lau, S ; Shum, H P ; Chan, C C Y ; Man, M Y ; Tang, K B ; Chan, K K C ; Leung, A K H ; Yan, W W</creator><creatorcontrib>Lau, S ; Shum, H P ; Chan, C C Y ; Man, M Y ; Tang, K B ; Chan, K K C ; Leung, A K H ; Yan, W W</creatorcontrib><description>This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong.
This retrospective analysis included all patients admitted to the intensive care unit of Pamela Youde Nethersole Eastern Hospital from January 2010 to December 2019. The ANN model was constructed using parameters identical to the APACHE IV model. Discrimination performance was assessed using area under the receiver operating characteristic curve (AUROC); calibration performance was evaluated using the Brier score and Hosmer-Lemeshow statistic.
In total, 14 503 patients were included, with 10% in the validation set and 90% in the ANN model development set. The ANN model (AUROC=0.88, 95% confidence interval [CI]=0.86-0.90, Brier score=0.10; P in Hosmer-Lemeshow test=0.37) outperformed the APACHE II model (AUROC=0.85, 95% CI=0.80-0.85, Brier score=0.14; P<0.001 for both comparisons of AUROCs and Brier scores) but showed performance similar to the APACHE IV model (AUROC=0.87, 95% CI=0.85-0.89, Brier score=0.11; P=0.34 for comparison of AUROCs, and P=0.05 for comparison of Brier scores). The ANN model demonstrated better calibration than the APACHE II and APACHE IV models.
Our ANN model outperformed the APACHE II model but was similar to the APACHE IV model in terms of predicting hospital mortality in Hong Kong. Artificial neural networks are valuable tools that can enhance real-time prognostic prediction.</description><identifier>ISSN: 1024-2708</identifier><identifier>EISSN: 2226-8707</identifier><identifier>DOI: 10.12809/hkmj2210235</identifier><identifier>PMID: 38545639</identifier><language>eng</language><publisher>China: Hong Kong Academy of Medicine</publisher><subject>Aged ; Algorithms ; APACHE ; Area Under Curve ; Calibration ; Clinical outcomes ; Critical Illness - mortality ; Female ; Hong Kong - epidemiology ; Hospital Mortality ; Hospitals ; Humans ; Intensive care ; Intensive Care Units - statistics & numerical data ; Logistic Models ; Machine learning ; Male ; Middle Aged ; Missing data ; Mortality ; Neural networks ; Neural Networks, Computer ; Patients ; Physiology ; Regression analysis ; Retrospective Studies ; ROC Curve ; Software ; Variables</subject><ispartof>Hong Kong Medical Journal, 2024-04, Vol.30 (2), p.130-138</ispartof><rights>2024. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,860,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38545639$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Lau, S</creatorcontrib><creatorcontrib>Shum, H P</creatorcontrib><creatorcontrib>Chan, C C Y</creatorcontrib><creatorcontrib>Man, M Y</creatorcontrib><creatorcontrib>Tang, K B</creatorcontrib><creatorcontrib>Chan, K K C</creatorcontrib><creatorcontrib>Leung, A K H</creatorcontrib><creatorcontrib>Yan, W W</creatorcontrib><title>Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model</title><title>Hong Kong Medical Journal</title><addtitle>Hong Kong Med J</addtitle><description>This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong.
This retrospective analysis included all patients admitted to the intensive care unit of Pamela Youde Nethersole Eastern Hospital from January 2010 to December 2019. The ANN model was constructed using parameters identical to the APACHE IV model. Discrimination performance was assessed using area under the receiver operating characteristic curve (AUROC); calibration performance was evaluated using the Brier score and Hosmer-Lemeshow statistic.
In total, 14 503 patients were included, with 10% in the validation set and 90% in the ANN model development set. The ANN model (AUROC=0.88, 95% confidence interval [CI]=0.86-0.90, Brier score=0.10; P in Hosmer-Lemeshow test=0.37) outperformed the APACHE II model (AUROC=0.85, 95% CI=0.80-0.85, Brier score=0.14; P<0.001 for both comparisons of AUROCs and Brier scores) but showed performance similar to the APACHE IV model (AUROC=0.87, 95% CI=0.85-0.89, Brier score=0.11; P=0.34 for comparison of AUROCs, and P=0.05 for comparison of Brier scores). The ANN model demonstrated better calibration than the APACHE II and APACHE IV models.
Our ANN model outperformed the APACHE II model but was similar to the APACHE IV model in terms of predicting hospital mortality in Hong Kong. Artificial neural networks are valuable tools that can enhance real-time prognostic prediction.</description><subject>Aged</subject><subject>Algorithms</subject><subject>APACHE</subject><subject>Area Under Curve</subject><subject>Calibration</subject><subject>Clinical outcomes</subject><subject>Critical Illness - mortality</subject><subject>Female</subject><subject>Hong Kong - epidemiology</subject><subject>Hospital Mortality</subject><subject>Hospitals</subject><subject>Humans</subject><subject>Intensive care</subject><subject>Intensive Care Units - statistics & numerical data</subject><subject>Logistic Models</subject><subject>Machine learning</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Missing data</subject><subject>Mortality</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Patients</subject><subject>Physiology</subject><subject>Regression analysis</subject><subject>Retrospective Studies</subject><subject>ROC Curve</subject><subject>Software</subject><subject>Variables</subject><issn>1024-2708</issn><issn>2226-8707</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>BENPR</sourceid><recordid>eNpdkU1v1DAYhC1ERZfCjTOyxIUDAX_EG4dbVfElVWoPcI7eOG-279aJg-2o2l_E36zpFoQ4jTR6NDPSMPZKivdSWdF-uLmd9kpJobR5wjZKqW1lG9E8ZZvi1ZVqhD1lz1PaC6GsacUzdqqtqc1Wtxv26zriQC5TmHkY-U1IC2XwfAqxCOUDhynMO-4iZXLg_YGT93yBTDjnxGnmwBPNO4_cFSfib-s8EXzkLkwLRErHaIiZRnJUwmdc44PkuxBvE4d54D7sKJUKHnEXMaUyqOoh4VCmDOhfsJMRfMKXj3rGfnz-9P3ia3V59eXbxfll5bSsc2WtQTkoVaPSOI7gBmOsxGELwqAatTCiRmhr07coNUCtRtu73hkDSjkEfcbeHnOXGH6umHI3UXLoPcwY1tRpIWshrLK2oG_-Q_dhjXNZ12kplWy0Nk2h3h0pF0NKEcduiTRBPHRSdA8Hdv8cWPDXj6FrP-HwF_7zmL4HbIyatA</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Lau, S</creator><creator>Shum, H P</creator><creator>Chan, C C Y</creator><creator>Man, M Y</creator><creator>Tang, K B</creator><creator>Chan, K K C</creator><creator>Leung, A K H</creator><creator>Yan, W W</creator><general>Hong Kong Academy of Medicine</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>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BVBZV</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope></search><sort><creationdate>20240401</creationdate><title>Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model</title><author>Lau, S ; Shum, H P ; Chan, C C Y ; Man, M Y ; Tang, K B ; Chan, K K C ; Leung, A K H ; Yan, W W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c314t-885e1d224e23effacd5581ed6a05e2f30504ea945b9e13aa42f8bcbc55a22cea3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Aged</topic><topic>Algorithms</topic><topic>APACHE</topic><topic>Area Under Curve</topic><topic>Calibration</topic><topic>Clinical outcomes</topic><topic>Critical Illness - mortality</topic><topic>Female</topic><topic>Hong Kong - epidemiology</topic><topic>Hospital Mortality</topic><topic>Hospitals</topic><topic>Humans</topic><topic>Intensive care</topic><topic>Intensive Care Units - statistics & numerical data</topic><topic>Logistic Models</topic><topic>Machine learning</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Missing data</topic><topic>Mortality</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Patients</topic><topic>Physiology</topic><topic>Regression analysis</topic><topic>Retrospective Studies</topic><topic>ROC Curve</topic><topic>Software</topic><topic>Variables</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lau, S</creatorcontrib><creatorcontrib>Shum, H P</creatorcontrib><creatorcontrib>Chan, C C Y</creatorcontrib><creatorcontrib>Man, M Y</creatorcontrib><creatorcontrib>Tang, K B</creatorcontrib><creatorcontrib>Chan, K K C</creatorcontrib><creatorcontrib>Leung, A K H</creatorcontrib><creatorcontrib>Yan, W W</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 & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</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 Essentials</collection><collection>ProQuest Central</collection><collection>East & South Asia Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</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>Publicly Available Content 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><jtitle>Hong Kong Medical Journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lau, S</au><au>Shum, H P</au><au>Chan, C C Y</au><au>Man, M Y</au><au>Tang, K B</au><au>Chan, K K C</au><au>Leung, A K H</au><au>Yan, W W</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model</atitle><jtitle>Hong Kong Medical Journal</jtitle><addtitle>Hong Kong Med J</addtitle><date>2024-04-01</date><risdate>2024</risdate><volume>30</volume><issue>2</issue><spage>130</spage><epage>138</epage><pages>130-138</pages><issn>1024-2708</issn><eissn>2226-8707</eissn><abstract>This study compared the performance of the artificial neural network (ANN) model with the Acute Physiologic and Chronic Health Evaluation (APACHE) II and IV models for predicting hospital mortality among critically ill patients in Hong Kong.
This retrospective analysis included all patients admitted to the intensive care unit of Pamela Youde Nethersole Eastern Hospital from January 2010 to December 2019. The ANN model was constructed using parameters identical to the APACHE IV model. Discrimination performance was assessed using area under the receiver operating characteristic curve (AUROC); calibration performance was evaluated using the Brier score and Hosmer-Lemeshow statistic.
In total, 14 503 patients were included, with 10% in the validation set and 90% in the ANN model development set. The ANN model (AUROC=0.88, 95% confidence interval [CI]=0.86-0.90, Brier score=0.10; P in Hosmer-Lemeshow test=0.37) outperformed the APACHE II model (AUROC=0.85, 95% CI=0.80-0.85, Brier score=0.14; P<0.001 for both comparisons of AUROCs and Brier scores) but showed performance similar to the APACHE IV model (AUROC=0.87, 95% CI=0.85-0.89, Brier score=0.11; P=0.34 for comparison of AUROCs, and P=0.05 for comparison of Brier scores). The ANN model demonstrated better calibration than the APACHE II and APACHE IV models.
Our ANN model outperformed the APACHE II model but was similar to the APACHE IV model in terms of predicting hospital mortality in Hong Kong. Artificial neural networks are valuable tools that can enhance real-time prognostic prediction.</abstract><cop>China</cop><pub>Hong Kong Academy of Medicine</pub><pmid>38545639</pmid><doi>10.12809/hkmj2210235</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1024-2708 |
| ispartof | Hong Kong Medical Journal, 2024-04, Vol.30 (2), p.130-138 |
| issn | 1024-2708 2226-8707 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_3014008288 |
| source | MEDLINE; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Aged Algorithms APACHE Area Under Curve Calibration Clinical outcomes Critical Illness - mortality Female Hong Kong - epidemiology Hospital Mortality Hospitals Humans Intensive care Intensive Care Units - statistics & numerical data Logistic Models Machine learning Male Middle Aged Missing data Mortality Neural networks Neural Networks, Computer Patients Physiology Regression analysis Retrospective Studies ROC Curve Software Variables |
| title | Prediction of hospital mortality among critically ill patients in a single centre in Asia: comparison of artificial neural networks and logistic regression-based model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T23%3A57%3A03IST&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=Prediction%20of%20hospital%20mortality%20among%20critically%20ill%20patients%20in%20a%20single%20centre%20in%20Asia:%20comparison%20of%20artificial%20neural%20networks%20and%20logistic%20regression-based%20model&rft.jtitle=Hong%20Kong%20Medical%20Journal&rft.au=Lau,%20S&rft.date=2024-04-01&rft.volume=30&rft.issue=2&rft.spage=130&rft.epage=138&rft.pages=130-138&rft.issn=1024-2708&rft.eissn=2226-8707&rft_id=info:doi/10.12809/hkmj2210235&rft_dat=%3Cproquest_cross%3E3014008288%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=3112173357&rft_id=info:pmid/38545639&rfr_iscdi=true |