Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study

Background Bayesian networks (BNs) are machine-learning–based computational models that visualize causal relationships and provide insight into the processes underlying disease progression, closely resembling clinical decision-making. Preoperative identification of patients at risk for lymph node me...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Reijnen, Casper, Gogou, Evangelia, Visser, Nicole C M, Engerud, Hilde, Ramjith, Jordache, van der Putten, Louis J M, Van de Vijver, Koen, Santacana, Maria, Bronsert, Peter, Bulten, Johan, Hirschfeld, Marc, Colas, Eva, Gil-Moreno, Antonio, Reques, Armando, Mancebo, Gemma, Krakstad, Camilla, Trovik, Jone, Haldorsen, Ingfrid S, Huvila, Jutta, Koskas, Martin, Weinberger, Vit, Bednarikova, Marketa, Hausnerova, Jitka, van der Wurff, Anneke A M, Matias-Guiu, Xavier, Amant, Frederic, Massuger, Leon F A G, Snijders, Marc P L M, Kusters-Vandevelde, Heidi V N, Lucas, Peter J F, Pijnenborg, Johanna M A
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Reijnen, Casper
Gogou, Evangelia
Visser, Nicole C M
Engerud, Hilde
Ramjith, Jordache
van der Putten, Louis J M
Van de Vijver, Koen
Santacana, Maria
Bronsert, Peter
Bulten, Johan
Hirschfeld, Marc
Colas, Eva
Gil-Moreno, Antonio
Reques, Armando
Mancebo, Gemma
Krakstad, Camilla
Trovik, Jone
Haldorsen, Ingfrid S
Huvila, Jutta
Koskas, Martin
Weinberger, Vit
Bednarikova, Marketa
Hausnerova, Jitka
van der Wurff, Anneke A M
Matias-Guiu, Xavier
Amant, Frederic
Massuger, Leon F A G
Snijders, Marc P L M
Kusters-Vandevelde, Heidi V N
Lucas, Peter J F
Pijnenborg, Johanna M A
description Background Bayesian networks (BNs) are machine-learning–based computational models that visualize causal relationships and provide insight into the processes underlying disease progression, closely resembling clinical decision-making. Preoperative identification of patients at risk for lymph node metastasis (LNM) is challenging in endometrial cancer, and although several biomarkers are related to LNM, none of them are incorporated in clinical practice. The aim of this study was to develop and externally validate a preoperative BN to predict LNM and outcome in endometrial cancer patients. Methods and findings Within the European Network for Individualized Treatment of Endometrial Cancer (ENITEC), we performed a retrospective multicenter cohort study including 763 patients, median age 65 years (interquartile range [IQR] 58–71), surgically treated for endometrial cancer between February 1995 and August 2013 at one of the 10 participating European hospitals. A BN was developed using score-based machine learning in addition to expert knowledge. Our main outcome measures were LNM and 5-year disease-specific survival (DSS). Preoperative clinical, histopathological, and molecular biomarkers were included in the network. External validation was performed using 2 prospective study cohorts: the Molecular Markers in Treatment in Endometrial Cancer (MoMaTEC) study cohort, including 446 Norwegian patients, median age 64 years (IQR 59–74), treated between May 2001 and 2010; and the PIpelle Prospective ENDOmetrial carcinoma (PIPENDO) study cohort, including 384 Dutch patients, median age 66 years (IQR 60–73), treated between September 2011 and December 2013. A BN called ENDORISK (preoperative risk stratification in endometrial cancer) was developed including the following predictors: preoperative tumor grade; immunohistochemical expression of estrogen receptor (ER), progesterone receptor (PR), p53, and L1 cell adhesion molecule (L1CAM); cancer antigen 125 serum level; thrombocyte count; imaging results on lymphadenopathy; and cervical cytology. In the MoMaTEC cohort, the area under the curve (AUC) was 0.82 (95% confidence interval [CI] 0.76–0.88) for LNM and 0.82 (95% CI 0.77–0.87) for 5-year DSS. In the PIPENDO cohort, the AUC for 5-year DSS was 0.84 (95% CI 0.78–0.90). The network was well-calibrated. In the MoMaTEC cohort, 249 patients (55.8%) were classified with
format Article
fullrecord <record><control><sourceid>ghent</sourceid><recordid>TN_cdi_ghent_librecat_oai_archive_ugent_be_8662482</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_archive_ugent_be_8662482</sourcerecordid><originalsourceid>FETCH-ghent_librecat_oai_archive_ugent_be_86624823</originalsourceid><addsrcrecordid>eNqdjk9PAjEUxHuABBS-wzvigWSp_FuPCkZjAga9N2-3D3jQbUlb1uzVT06JfgIuM5n8MpNpie5oMs6HIzmbdcRdCIcsk3mWZ13x--nJnchj5JrAczhCiNe05TKps8AWyGpXUfSMBkq0JXkYLFeL9eb96-MBigYQnrGhwGjBUvxx_giV02TgKSFNNRl3qshGQKuhRsP6bzvEs256or1FE6j_7_dCvi6_X96Gu32qKMOFp_RFOWSFvtyno-q8u6KC1Hw6leO5fLypdAGvoF0n</addsrcrecordid><sourcetype>Institutional Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study</title><source>Ghent University Academic Bibliography</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>Public Library of Science (PLoS)</source><creator>Reijnen, Casper ; Gogou, Evangelia ; Visser, Nicole C M ; Engerud, Hilde ; Ramjith, Jordache ; van der Putten, Louis J M ; Van de Vijver, Koen ; Santacana, Maria ; Bronsert, Peter ; Bulten, Johan ; Hirschfeld, Marc ; Colas, Eva ; Gil-Moreno, Antonio ; Reques, Armando ; Mancebo, Gemma ; Krakstad, Camilla ; Trovik, Jone ; Haldorsen, Ingfrid S ; Huvila, Jutta ; Koskas, Martin ; Weinberger, Vit ; Bednarikova, Marketa ; Hausnerova, Jitka ; van der Wurff, Anneke A M ; Matias-Guiu, Xavier ; Amant, Frederic ; Massuger, Leon F A G ; Snijders, Marc P L M ; Kusters-Vandevelde, Heidi V N ; Lucas, Peter J F ; Pijnenborg, Johanna M A</creator><creatorcontrib>Reijnen, Casper ; Gogou, Evangelia ; Visser, Nicole C M ; Engerud, Hilde ; Ramjith, Jordache ; van der Putten, Louis J M ; Van de Vijver, Koen ; Santacana, Maria ; Bronsert, Peter ; Bulten, Johan ; Hirschfeld, Marc ; Colas, Eva ; Gil-Moreno, Antonio ; Reques, Armando ; Mancebo, Gemma ; Krakstad, Camilla ; Trovik, Jone ; Haldorsen, Ingfrid S ; Huvila, Jutta ; Koskas, Martin ; Weinberger, Vit ; Bednarikova, Marketa ; Hausnerova, Jitka ; van der Wurff, Anneke A M ; Matias-Guiu, Xavier ; Amant, Frederic ; Massuger, Leon F A G ; Snijders, Marc P L M ; Kusters-Vandevelde, Heidi V N ; Lucas, Peter J F ; Pijnenborg, Johanna M A</creatorcontrib><description>Background Bayesian networks (BNs) are machine-learning–based computational models that visualize causal relationships and provide insight into the processes underlying disease progression, closely resembling clinical decision-making. Preoperative identification of patients at risk for lymph node metastasis (LNM) is challenging in endometrial cancer, and although several biomarkers are related to LNM, none of them are incorporated in clinical practice. The aim of this study was to develop and externally validate a preoperative BN to predict LNM and outcome in endometrial cancer patients. Methods and findings Within the European Network for Individualized Treatment of Endometrial Cancer (ENITEC), we performed a retrospective multicenter cohort study including 763 patients, median age 65 years (interquartile range [IQR] 58–71), surgically treated for endometrial cancer between February 1995 and August 2013 at one of the 10 participating European hospitals. A BN was developed using score-based machine learning in addition to expert knowledge. Our main outcome measures were LNM and 5-year disease-specific survival (DSS). Preoperative clinical, histopathological, and molecular biomarkers were included in the network. External validation was performed using 2 prospective study cohorts: the Molecular Markers in Treatment in Endometrial Cancer (MoMaTEC) study cohort, including 446 Norwegian patients, median age 64 years (IQR 59–74), treated between May 2001 and 2010; and the PIpelle Prospective ENDOmetrial carcinoma (PIPENDO) study cohort, including 384 Dutch patients, median age 66 years (IQR 60–73), treated between September 2011 and December 2013. A BN called ENDORISK (preoperative risk stratification in endometrial cancer) was developed including the following predictors: preoperative tumor grade; immunohistochemical expression of estrogen receptor (ER), progesterone receptor (PR), p53, and L1 cell adhesion molecule (L1CAM); cancer antigen 125 serum level; thrombocyte count; imaging results on lymphadenopathy; and cervical cytology. In the MoMaTEC cohort, the area under the curve (AUC) was 0.82 (95% confidence interval [CI] 0.76–0.88) for LNM and 0.82 (95% CI 0.77–0.87) for 5-year DSS. In the PIPENDO cohort, the AUC for 5-year DSS was 0.84 (95% CI 0.78–0.90). The network was well-calibrated. In the MoMaTEC cohort, 249 patients (55.8%) were classified with &lt;5% risk of LNM, with a false-negative rate of 1.6%. A limitation of the study is the use of imputation to correct for missing predictor variables in the development cohort and the retrospective study design. Conclusions In this study, we illustrated how BNs can be used for individualizing clinical decision-making in oncology by incorporating easily accessible and multimodal biomarkers. The network shows the complex interactions underlying the carcinogenetic process of endometrial cancer by its graphical representation. A prospective feasibility study will be needed prior to implementation in the clinic.</description><identifier>ISSN: 1549-1277</identifier><identifier>ISSN: 1549-1676</identifier><language>eng</language><subject>CARCINOMA ; L1CAM ; LYMPH-NODE METASTASIS ; Medicine and Health Sciences ; PREDICTION</subject><creationdate>2020</creationdate><rights>Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) info:eu-repo/semantics/openAccess</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>314,315,776,780,4010,27837</link.rule.ids></links><search><creatorcontrib>Reijnen, Casper</creatorcontrib><creatorcontrib>Gogou, Evangelia</creatorcontrib><creatorcontrib>Visser, Nicole C M</creatorcontrib><creatorcontrib>Engerud, Hilde</creatorcontrib><creatorcontrib>Ramjith, Jordache</creatorcontrib><creatorcontrib>van der Putten, Louis J M</creatorcontrib><creatorcontrib>Van de Vijver, Koen</creatorcontrib><creatorcontrib>Santacana, Maria</creatorcontrib><creatorcontrib>Bronsert, Peter</creatorcontrib><creatorcontrib>Bulten, Johan</creatorcontrib><creatorcontrib>Hirschfeld, Marc</creatorcontrib><creatorcontrib>Colas, Eva</creatorcontrib><creatorcontrib>Gil-Moreno, Antonio</creatorcontrib><creatorcontrib>Reques, Armando</creatorcontrib><creatorcontrib>Mancebo, Gemma</creatorcontrib><creatorcontrib>Krakstad, Camilla</creatorcontrib><creatorcontrib>Trovik, Jone</creatorcontrib><creatorcontrib>Haldorsen, Ingfrid S</creatorcontrib><creatorcontrib>Huvila, Jutta</creatorcontrib><creatorcontrib>Koskas, Martin</creatorcontrib><creatorcontrib>Weinberger, Vit</creatorcontrib><creatorcontrib>Bednarikova, Marketa</creatorcontrib><creatorcontrib>Hausnerova, Jitka</creatorcontrib><creatorcontrib>van der Wurff, Anneke A M</creatorcontrib><creatorcontrib>Matias-Guiu, Xavier</creatorcontrib><creatorcontrib>Amant, Frederic</creatorcontrib><creatorcontrib>Massuger, Leon F A G</creatorcontrib><creatorcontrib>Snijders, Marc P L M</creatorcontrib><creatorcontrib>Kusters-Vandevelde, Heidi V N</creatorcontrib><creatorcontrib>Lucas, Peter J F</creatorcontrib><creatorcontrib>Pijnenborg, Johanna M A</creatorcontrib><title>Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study</title><description>Background Bayesian networks (BNs) are machine-learning–based computational models that visualize causal relationships and provide insight into the processes underlying disease progression, closely resembling clinical decision-making. Preoperative identification of patients at risk for lymph node metastasis (LNM) is challenging in endometrial cancer, and although several biomarkers are related to LNM, none of them are incorporated in clinical practice. The aim of this study was to develop and externally validate a preoperative BN to predict LNM and outcome in endometrial cancer patients. Methods and findings Within the European Network for Individualized Treatment of Endometrial Cancer (ENITEC), we performed a retrospective multicenter cohort study including 763 patients, median age 65 years (interquartile range [IQR] 58–71), surgically treated for endometrial cancer between February 1995 and August 2013 at one of the 10 participating European hospitals. A BN was developed using score-based machine learning in addition to expert knowledge. Our main outcome measures were LNM and 5-year disease-specific survival (DSS). Preoperative clinical, histopathological, and molecular biomarkers were included in the network. External validation was performed using 2 prospective study cohorts: the Molecular Markers in Treatment in Endometrial Cancer (MoMaTEC) study cohort, including 446 Norwegian patients, median age 64 years (IQR 59–74), treated between May 2001 and 2010; and the PIpelle Prospective ENDOmetrial carcinoma (PIPENDO) study cohort, including 384 Dutch patients, median age 66 years (IQR 60–73), treated between September 2011 and December 2013. A BN called ENDORISK (preoperative risk stratification in endometrial cancer) was developed including the following predictors: preoperative tumor grade; immunohistochemical expression of estrogen receptor (ER), progesterone receptor (PR), p53, and L1 cell adhesion molecule (L1CAM); cancer antigen 125 serum level; thrombocyte count; imaging results on lymphadenopathy; and cervical cytology. In the MoMaTEC cohort, the area under the curve (AUC) was 0.82 (95% confidence interval [CI] 0.76–0.88) for LNM and 0.82 (95% CI 0.77–0.87) for 5-year DSS. In the PIPENDO cohort, the AUC for 5-year DSS was 0.84 (95% CI 0.78–0.90). The network was well-calibrated. In the MoMaTEC cohort, 249 patients (55.8%) were classified with &lt;5% risk of LNM, with a false-negative rate of 1.6%. A limitation of the study is the use of imputation to correct for missing predictor variables in the development cohort and the retrospective study design. Conclusions In this study, we illustrated how BNs can be used for individualizing clinical decision-making in oncology by incorporating easily accessible and multimodal biomarkers. The network shows the complex interactions underlying the carcinogenetic process of endometrial cancer by its graphical representation. A prospective feasibility study will be needed prior to implementation in the clinic.</description><subject>CARCINOMA</subject><subject>L1CAM</subject><subject>LYMPH-NODE METASTASIS</subject><subject>Medicine and Health Sciences</subject><subject>PREDICTION</subject><issn>1549-1277</issn><issn>1549-1676</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ADGLB</sourceid><recordid>eNqdjk9PAjEUxHuABBS-wzvigWSp_FuPCkZjAga9N2-3D3jQbUlb1uzVT06JfgIuM5n8MpNpie5oMs6HIzmbdcRdCIcsk3mWZ13x--nJnchj5JrAczhCiNe05TKps8AWyGpXUfSMBkq0JXkYLFeL9eb96-MBigYQnrGhwGjBUvxx_giV02TgKSFNNRl3qshGQKuhRsP6bzvEs256or1FE6j_7_dCvi6_X96Gu32qKMOFp_RFOWSFvtyno-q8u6KC1Hw6leO5fLypdAGvoF0n</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Reijnen, Casper</creator><creator>Gogou, Evangelia</creator><creator>Visser, Nicole C M</creator><creator>Engerud, Hilde</creator><creator>Ramjith, Jordache</creator><creator>van der Putten, Louis J M</creator><creator>Van de Vijver, Koen</creator><creator>Santacana, Maria</creator><creator>Bronsert, Peter</creator><creator>Bulten, Johan</creator><creator>Hirschfeld, Marc</creator><creator>Colas, Eva</creator><creator>Gil-Moreno, Antonio</creator><creator>Reques, Armando</creator><creator>Mancebo, Gemma</creator><creator>Krakstad, Camilla</creator><creator>Trovik, Jone</creator><creator>Haldorsen, Ingfrid S</creator><creator>Huvila, Jutta</creator><creator>Koskas, Martin</creator><creator>Weinberger, Vit</creator><creator>Bednarikova, Marketa</creator><creator>Hausnerova, Jitka</creator><creator>van der Wurff, Anneke A M</creator><creator>Matias-Guiu, Xavier</creator><creator>Amant, Frederic</creator><creator>Massuger, Leon F A G</creator><creator>Snijders, Marc P L M</creator><creator>Kusters-Vandevelde, Heidi V N</creator><creator>Lucas, Peter J F</creator><creator>Pijnenborg, Johanna M A</creator><scope>ADGLB</scope></search><sort><creationdate>2020</creationdate><title>Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study</title><author>Reijnen, Casper ; Gogou, Evangelia ; Visser, Nicole C M ; Engerud, Hilde ; Ramjith, Jordache ; van der Putten, Louis J M ; Van de Vijver, Koen ; Santacana, Maria ; Bronsert, Peter ; Bulten, Johan ; Hirschfeld, Marc ; Colas, Eva ; Gil-Moreno, Antonio ; Reques, Armando ; Mancebo, Gemma ; Krakstad, Camilla ; Trovik, Jone ; Haldorsen, Ingfrid S ; Huvila, Jutta ; Koskas, Martin ; Weinberger, Vit ; Bednarikova, Marketa ; Hausnerova, Jitka ; van der Wurff, Anneke A M ; Matias-Guiu, Xavier ; Amant, Frederic ; Massuger, Leon F A G ; Snijders, Marc P L M ; Kusters-Vandevelde, Heidi V N ; Lucas, Peter J F ; Pijnenborg, Johanna M A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ghent_librecat_oai_archive_ugent_be_86624823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>CARCINOMA</topic><topic>L1CAM</topic><topic>LYMPH-NODE METASTASIS</topic><topic>Medicine and Health Sciences</topic><topic>PREDICTION</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Reijnen, Casper</creatorcontrib><creatorcontrib>Gogou, Evangelia</creatorcontrib><creatorcontrib>Visser, Nicole C M</creatorcontrib><creatorcontrib>Engerud, Hilde</creatorcontrib><creatorcontrib>Ramjith, Jordache</creatorcontrib><creatorcontrib>van der Putten, Louis J M</creatorcontrib><creatorcontrib>Van de Vijver, Koen</creatorcontrib><creatorcontrib>Santacana, Maria</creatorcontrib><creatorcontrib>Bronsert, Peter</creatorcontrib><creatorcontrib>Bulten, Johan</creatorcontrib><creatorcontrib>Hirschfeld, Marc</creatorcontrib><creatorcontrib>Colas, Eva</creatorcontrib><creatorcontrib>Gil-Moreno, Antonio</creatorcontrib><creatorcontrib>Reques, Armando</creatorcontrib><creatorcontrib>Mancebo, Gemma</creatorcontrib><creatorcontrib>Krakstad, Camilla</creatorcontrib><creatorcontrib>Trovik, Jone</creatorcontrib><creatorcontrib>Haldorsen, Ingfrid S</creatorcontrib><creatorcontrib>Huvila, Jutta</creatorcontrib><creatorcontrib>Koskas, Martin</creatorcontrib><creatorcontrib>Weinberger, Vit</creatorcontrib><creatorcontrib>Bednarikova, Marketa</creatorcontrib><creatorcontrib>Hausnerova, Jitka</creatorcontrib><creatorcontrib>van der Wurff, Anneke A M</creatorcontrib><creatorcontrib>Matias-Guiu, Xavier</creatorcontrib><creatorcontrib>Amant, Frederic</creatorcontrib><creatorcontrib>Massuger, Leon F A G</creatorcontrib><creatorcontrib>Snijders, Marc P L M</creatorcontrib><creatorcontrib>Kusters-Vandevelde, Heidi V N</creatorcontrib><creatorcontrib>Lucas, Peter J F</creatorcontrib><creatorcontrib>Pijnenborg, Johanna M A</creatorcontrib><collection>Ghent University Academic Bibliography</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Reijnen, Casper</au><au>Gogou, Evangelia</au><au>Visser, Nicole C M</au><au>Engerud, Hilde</au><au>Ramjith, Jordache</au><au>van der Putten, Louis J M</au><au>Van de Vijver, Koen</au><au>Santacana, Maria</au><au>Bronsert, Peter</au><au>Bulten, Johan</au><au>Hirschfeld, Marc</au><au>Colas, Eva</au><au>Gil-Moreno, Antonio</au><au>Reques, Armando</au><au>Mancebo, Gemma</au><au>Krakstad, Camilla</au><au>Trovik, Jone</au><au>Haldorsen, Ingfrid S</au><au>Huvila, Jutta</au><au>Koskas, Martin</au><au>Weinberger, Vit</au><au>Bednarikova, Marketa</au><au>Hausnerova, Jitka</au><au>van der Wurff, Anneke A M</au><au>Matias-Guiu, Xavier</au><au>Amant, Frederic</au><au>Massuger, Leon F A G</au><au>Snijders, Marc P L M</au><au>Kusters-Vandevelde, Heidi V N</au><au>Lucas, Peter J F</au><au>Pijnenborg, Johanna M A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study</atitle><date>2020</date><risdate>2020</risdate><issn>1549-1277</issn><issn>1549-1676</issn><abstract>Background Bayesian networks (BNs) are machine-learning–based computational models that visualize causal relationships and provide insight into the processes underlying disease progression, closely resembling clinical decision-making. Preoperative identification of patients at risk for lymph node metastasis (LNM) is challenging in endometrial cancer, and although several biomarkers are related to LNM, none of them are incorporated in clinical practice. The aim of this study was to develop and externally validate a preoperative BN to predict LNM and outcome in endometrial cancer patients. Methods and findings Within the European Network for Individualized Treatment of Endometrial Cancer (ENITEC), we performed a retrospective multicenter cohort study including 763 patients, median age 65 years (interquartile range [IQR] 58–71), surgically treated for endometrial cancer between February 1995 and August 2013 at one of the 10 participating European hospitals. A BN was developed using score-based machine learning in addition to expert knowledge. Our main outcome measures were LNM and 5-year disease-specific survival (DSS). Preoperative clinical, histopathological, and molecular biomarkers were included in the network. External validation was performed using 2 prospective study cohorts: the Molecular Markers in Treatment in Endometrial Cancer (MoMaTEC) study cohort, including 446 Norwegian patients, median age 64 years (IQR 59–74), treated between May 2001 and 2010; and the PIpelle Prospective ENDOmetrial carcinoma (PIPENDO) study cohort, including 384 Dutch patients, median age 66 years (IQR 60–73), treated between September 2011 and December 2013. A BN called ENDORISK (preoperative risk stratification in endometrial cancer) was developed including the following predictors: preoperative tumor grade; immunohistochemical expression of estrogen receptor (ER), progesterone receptor (PR), p53, and L1 cell adhesion molecule (L1CAM); cancer antigen 125 serum level; thrombocyte count; imaging results on lymphadenopathy; and cervical cytology. In the MoMaTEC cohort, the area under the curve (AUC) was 0.82 (95% confidence interval [CI] 0.76–0.88) for LNM and 0.82 (95% CI 0.77–0.87) for 5-year DSS. In the PIPENDO cohort, the AUC for 5-year DSS was 0.84 (95% CI 0.78–0.90). The network was well-calibrated. In the MoMaTEC cohort, 249 patients (55.8%) were classified with &lt;5% risk of LNM, with a false-negative rate of 1.6%. A limitation of the study is the use of imputation to correct for missing predictor variables in the development cohort and the retrospective study design. Conclusions In this study, we illustrated how BNs can be used for individualizing clinical decision-making in oncology by incorporating easily accessible and multimodal biomarkers. The network shows the complex interactions underlying the carcinogenetic process of endometrial cancer by its graphical representation. A prospective feasibility study will be needed prior to implementation in the clinic.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1549-1277
ispartof
issn 1549-1277
1549-1676
language eng
recordid cdi_ghent_librecat_oai_archive_ugent_be_8662482
source Ghent University Academic Bibliography; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; Public Library of Science (PLoS)
subjects CARCINOMA
L1CAM
LYMPH-NODE METASTASIS
Medicine and Health Sciences
PREDICTION
title Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model : a development and validation study
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T04%3A43%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ghent&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Preoperative%20risk%20stratification%20in%20endometrial%20cancer%20(ENDORISK)%20by%20a%20Bayesian%20network%20model%20:%20a%20development%20and%20validation%20study&rft.au=Reijnen,%20Casper&rft.date=2020&rft.issn=1549-1277&rft_id=info:doi/&rft_dat=%3Cghent%3Eoai_archive_ugent_be_8662482%3C/ghent%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true