Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy

Objectives To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction. Methods Data included 1144 participants with PALF enrolled during three phases of the PALF regi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of pediatric gastroenterology and nutrition 2024-02, Vol.78 (2), p.320-327
Hauptverfasser: Li, Ruosha, Wang, Jingyan, Zhang, Cuihong, Squires, James E., Belle, Steven H., Ning, Jing, Cai, Jianwen, Squires, Robert H.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 327
container_issue 2
container_start_page 320
container_title Journal of pediatric gastroenterology and nutrition
container_volume 78
creator Li, Ruosha
Wang, Jingyan
Zhang, Cuihong
Squires, James E.
Belle, Steven H.
Ning, Jing
Cai, Jianwen
Squires, Robert H.
description Objectives To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction. Methods Data included 1144 participants with PALF enrolled during three phases of the PALF registry study over 15 years. Using joint modeling, we built a dynamic prediction tool for mortality by combining longitudinal trajectories of multiple laboratory and clinical variables. The predictive performance for 7‐day and 21‐day mortality was assessed using the area under curve (AUC) through cross‐validation and split‐by‐time validation. Results We constructed a prognostic joint model that combines the temporal trajectories of international normalized ratio, total bilirubin, hepatic encephalopathy, platelet count, and serum creatinine. Dynamic prediction using updated information improved predictive performance over static prediction using the information at enrollment (Day 0) only. In cross‐validation, AUC increased from 0.784 to 0.887 when measurements obtained between Days 1 and 2 were incorporated. AUC remained similar when we used the earlier subset of the sample for training and the later subset for testing. Conclusions Serial measurements of five variables in the first few days of PALF capture the dynamic clinical course of the disease and improve risk prediction for mortality. Continuous disease monitoring and updating risk prognosis are beneficial for timely and judicious medical decisions. Visual What is Known Mortality risk prediction for PALF is critical for medical decision‐making. However, existing prognostic tools do not effectively utilize information in the rapid and heterogeneous clinical course of PALF. What is New A prognostic model is developed to capture the dynamic clinical course of PALF by integrating the trajectories of five longitudinal variables. The model achieves favorable performance in cross‐validation and temporal‐validation, facilitating early detection of high‐risk patients.
doi_str_mv 10.1002/jpn3.12094
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2928855209</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2928855209</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3294-89977b2e14dcef46e14c715699541411dde57182c0ba4fc6a85a159de5f187733</originalsourceid><addsrcrecordid>eNp9kMtOwzAQRS0EoqWw4QOQlwgpxePYsbNEiEdRBSxgHbmOU7nKCzspyt_jkoJYsZqHzlxpDkLnQOZACL3etHU8B0pSdoCmwOMkYpLAIZoSKkREAZIJOvF-QwgRjJNjNIllHDomp0gtqtY1W5PjqnGdKm034NaZ3OrONjUuGofbMKnOWY2V7juDS7s1DhfKlr0zuPe2XuN8qFUViD-nvnOqM-vhFB0VqvTmbF9n6P3-7u32MVq-PCxub5aRjmnKIpmmQqyoAZZrU7AkNFoAT9KUM2AAeW64AEk1WSlW6ERJroCnYVuAFCKOZ-hyzA3_fPTGd1llvTZlqWrT9D6jKZWS86ApoFcjql3jvTNF1jpbKTdkQLKd0mynNPtWGuCLfW6_qkz-i_44DACMwKctzfBPVPb0-hyPoV9L2oHz</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2928855209</pqid></control><display><type>article</type><title>Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy</title><source>MEDLINE</source><source>Access via Wiley Online Library</source><creator>Li, Ruosha ; Wang, Jingyan ; Zhang, Cuihong ; Squires, James E. ; Belle, Steven H. ; Ning, Jing ; Cai, Jianwen ; Squires, Robert H.</creator><creatorcontrib>Li, Ruosha ; Wang, Jingyan ; Zhang, Cuihong ; Squires, James E. ; Belle, Steven H. ; Ning, Jing ; Cai, Jianwen ; Squires, Robert H.</creatorcontrib><description>Objectives To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction. Methods Data included 1144 participants with PALF enrolled during three phases of the PALF registry study over 15 years. Using joint modeling, we built a dynamic prediction tool for mortality by combining longitudinal trajectories of multiple laboratory and clinical variables. The predictive performance for 7‐day and 21‐day mortality was assessed using the area under curve (AUC) through cross‐validation and split‐by‐time validation. Results We constructed a prognostic joint model that combines the temporal trajectories of international normalized ratio, total bilirubin, hepatic encephalopathy, platelet count, and serum creatinine. Dynamic prediction using updated information improved predictive performance over static prediction using the information at enrollment (Day 0) only. In cross‐validation, AUC increased from 0.784 to 0.887 when measurements obtained between Days 1 and 2 were incorporated. AUC remained similar when we used the earlier subset of the sample for training and the later subset for testing. Conclusions Serial measurements of five variables in the first few days of PALF capture the dynamic clinical course of the disease and improve risk prediction for mortality. Continuous disease monitoring and updating risk prognosis are beneficial for timely and judicious medical decisions. Visual What is Known Mortality risk prediction for PALF is critical for medical decision‐making. However, existing prognostic tools do not effectively utilize information in the rapid and heterogeneous clinical course of PALF. What is New A prognostic model is developed to capture the dynamic clinical course of PALF by integrating the trajectories of five longitudinal variables. The model achieves favorable performance in cross‐validation and temporal‐validation, facilitating early detection of high‐risk patients.</description><identifier>ISSN: 0277-2116</identifier><identifier>EISSN: 1536-4801</identifier><identifier>DOI: 10.1002/jpn3.12094</identifier><identifier>PMID: 38374548</identifier><language>eng</language><publisher>United States</publisher><subject>Bilirubin ; Child ; Disease Progression ; Hepatic Encephalopathy ; Humans ; joint model ; Liver Failure, Acute - diagnosis ; multiple variable trajectories ; PALF ; Prognosis ; validation</subject><ispartof>Journal of pediatric gastroenterology and nutrition, 2024-02, Vol.78 (2), p.320-327</ispartof><rights>2023 European Society for Pediatric Gastroenterology, Hepatology, and Nutrition and North American Society for Pediatric Gastroenterology, Hepatology, and Nutrition.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3294-89977b2e14dcef46e14c715699541411dde57182c0ba4fc6a85a159de5f187733</citedby><cites>FETCH-LOGICAL-c3294-89977b2e14dcef46e14c715699541411dde57182c0ba4fc6a85a159de5f187733</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fjpn3.12094$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fjpn3.12094$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38374548$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Ruosha</creatorcontrib><creatorcontrib>Wang, Jingyan</creatorcontrib><creatorcontrib>Zhang, Cuihong</creatorcontrib><creatorcontrib>Squires, James E.</creatorcontrib><creatorcontrib>Belle, Steven H.</creatorcontrib><creatorcontrib>Ning, Jing</creatorcontrib><creatorcontrib>Cai, Jianwen</creatorcontrib><creatorcontrib>Squires, Robert H.</creatorcontrib><title>Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy</title><title>Journal of pediatric gastroenterology and nutrition</title><addtitle>J Pediatr Gastroenterol Nutr</addtitle><description>Objectives To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction. Methods Data included 1144 participants with PALF enrolled during three phases of the PALF registry study over 15 years. Using joint modeling, we built a dynamic prediction tool for mortality by combining longitudinal trajectories of multiple laboratory and clinical variables. The predictive performance for 7‐day and 21‐day mortality was assessed using the area under curve (AUC) through cross‐validation and split‐by‐time validation. Results We constructed a prognostic joint model that combines the temporal trajectories of international normalized ratio, total bilirubin, hepatic encephalopathy, platelet count, and serum creatinine. Dynamic prediction using updated information improved predictive performance over static prediction using the information at enrollment (Day 0) only. In cross‐validation, AUC increased from 0.784 to 0.887 when measurements obtained between Days 1 and 2 were incorporated. AUC remained similar when we used the earlier subset of the sample for training and the later subset for testing. Conclusions Serial measurements of five variables in the first few days of PALF capture the dynamic clinical course of the disease and improve risk prediction for mortality. Continuous disease monitoring and updating risk prognosis are beneficial for timely and judicious medical decisions. Visual What is Known Mortality risk prediction for PALF is critical for medical decision‐making. However, existing prognostic tools do not effectively utilize information in the rapid and heterogeneous clinical course of PALF. What is New A prognostic model is developed to capture the dynamic clinical course of PALF by integrating the trajectories of five longitudinal variables. The model achieves favorable performance in cross‐validation and temporal‐validation, facilitating early detection of high‐risk patients.</description><subject>Bilirubin</subject><subject>Child</subject><subject>Disease Progression</subject><subject>Hepatic Encephalopathy</subject><subject>Humans</subject><subject>joint model</subject><subject>Liver Failure, Acute - diagnosis</subject><subject>multiple variable trajectories</subject><subject>PALF</subject><subject>Prognosis</subject><subject>validation</subject><issn>0277-2116</issn><issn>1536-4801</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kMtOwzAQRS0EoqWw4QOQlwgpxePYsbNEiEdRBSxgHbmOU7nKCzspyt_jkoJYsZqHzlxpDkLnQOZACL3etHU8B0pSdoCmwOMkYpLAIZoSKkREAZIJOvF-QwgRjJNjNIllHDomp0gtqtY1W5PjqnGdKm034NaZ3OrONjUuGofbMKnOWY2V7juDS7s1DhfKlr0zuPe2XuN8qFUViD-nvnOqM-vhFB0VqvTmbF9n6P3-7u32MVq-PCxub5aRjmnKIpmmQqyoAZZrU7AkNFoAT9KUM2AAeW64AEk1WSlW6ERJroCnYVuAFCKOZ-hyzA3_fPTGd1llvTZlqWrT9D6jKZWS86ApoFcjql3jvTNF1jpbKTdkQLKd0mynNPtWGuCLfW6_qkz-i_44DACMwKctzfBPVPb0-hyPoV9L2oHz</recordid><startdate>202402</startdate><enddate>202402</enddate><creator>Li, Ruosha</creator><creator>Wang, Jingyan</creator><creator>Zhang, Cuihong</creator><creator>Squires, James E.</creator><creator>Belle, Steven H.</creator><creator>Ning, Jing</creator><creator>Cai, Jianwen</creator><creator>Squires, Robert H.</creator><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></search><sort><creationdate>202402</creationdate><title>Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy</title><author>Li, Ruosha ; Wang, Jingyan ; Zhang, Cuihong ; Squires, James E. ; Belle, Steven H. ; Ning, Jing ; Cai, Jianwen ; Squires, Robert H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3294-89977b2e14dcef46e14c715699541411dde57182c0ba4fc6a85a159de5f187733</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Bilirubin</topic><topic>Child</topic><topic>Disease Progression</topic><topic>Hepatic Encephalopathy</topic><topic>Humans</topic><topic>joint model</topic><topic>Liver Failure, Acute - diagnosis</topic><topic>multiple variable trajectories</topic><topic>PALF</topic><topic>Prognosis</topic><topic>validation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Ruosha</creatorcontrib><creatorcontrib>Wang, Jingyan</creatorcontrib><creatorcontrib>Zhang, Cuihong</creatorcontrib><creatorcontrib>Squires, James E.</creatorcontrib><creatorcontrib>Belle, Steven H.</creatorcontrib><creatorcontrib>Ning, Jing</creatorcontrib><creatorcontrib>Cai, Jianwen</creatorcontrib><creatorcontrib>Squires, Robert 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>MEDLINE - Academic</collection><jtitle>Journal of pediatric gastroenterology and nutrition</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Ruosha</au><au>Wang, Jingyan</au><au>Zhang, Cuihong</au><au>Squires, James E.</au><au>Belle, Steven H.</au><au>Ning, Jing</au><au>Cai, Jianwen</au><au>Squires, Robert H.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy</atitle><jtitle>Journal of pediatric gastroenterology and nutrition</jtitle><addtitle>J Pediatr Gastroenterol Nutr</addtitle><date>2024-02</date><risdate>2024</risdate><volume>78</volume><issue>2</issue><spage>320</spage><epage>327</epage><pages>320-327</pages><issn>0277-2116</issn><eissn>1536-4801</eissn><abstract>Objectives To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction. Methods Data included 1144 participants with PALF enrolled during three phases of the PALF registry study over 15 years. Using joint modeling, we built a dynamic prediction tool for mortality by combining longitudinal trajectories of multiple laboratory and clinical variables. The predictive performance for 7‐day and 21‐day mortality was assessed using the area under curve (AUC) through cross‐validation and split‐by‐time validation. Results We constructed a prognostic joint model that combines the temporal trajectories of international normalized ratio, total bilirubin, hepatic encephalopathy, platelet count, and serum creatinine. Dynamic prediction using updated information improved predictive performance over static prediction using the information at enrollment (Day 0) only. In cross‐validation, AUC increased from 0.784 to 0.887 when measurements obtained between Days 1 and 2 were incorporated. AUC remained similar when we used the earlier subset of the sample for training and the later subset for testing. Conclusions Serial measurements of five variables in the first few days of PALF capture the dynamic clinical course of the disease and improve risk prediction for mortality. Continuous disease monitoring and updating risk prognosis are beneficial for timely and judicious medical decisions. Visual What is Known Mortality risk prediction for PALF is critical for medical decision‐making. However, existing prognostic tools do not effectively utilize information in the rapid and heterogeneous clinical course of PALF. What is New A prognostic model is developed to capture the dynamic clinical course of PALF by integrating the trajectories of five longitudinal variables. The model achieves favorable performance in cross‐validation and temporal‐validation, facilitating early detection of high‐risk patients.</abstract><cop>United States</cop><pmid>38374548</pmid><doi>10.1002/jpn3.12094</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0277-2116
ispartof Journal of pediatric gastroenterology and nutrition, 2024-02, Vol.78 (2), p.320-327
issn 0277-2116
1536-4801
language eng
recordid cdi_proquest_miscellaneous_2928855209
source MEDLINE; Access via Wiley Online Library
subjects Bilirubin
Child
Disease Progression
Hepatic Encephalopathy
Humans
joint model
Liver Failure, Acute - diagnosis
multiple variable trajectories
PALF
Prognosis
validation
title Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A48%3A23IST&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=Improved%20mortality%20prediction%20for%20pediatric%20acute%20liver%20failure%20using%20dynamic%20prediction%20strategy&rft.jtitle=Journal%20of%20pediatric%20gastroenterology%20and%20nutrition&rft.au=Li,%20Ruosha&rft.date=2024-02&rft.volume=78&rft.issue=2&rft.spage=320&rft.epage=327&rft.pages=320-327&rft.issn=0277-2116&rft.eissn=1536-4801&rft_id=info:doi/10.1002/jpn3.12094&rft_dat=%3Cproquest_cross%3E2928855209%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=2928855209&rft_id=info:pmid/38374548&rfr_iscdi=true