ENDORISK-2: A personalized Bayesian network for preoperative
risk stratification in endometrial cancer, integrating
molecular classification and preoperative myometrial invasion
assessment

J 2025

ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment

LOMBAERS, Marike S; Casper REIJNEN; Ally SPRIK; Petra BRETOVÁ; Marcel GRUBE et al.

Základní údaje

Originální název

ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment

Autoři

Vydání

European Journal of Cancer, London, ELSEVIER, 2025, 0959-8049

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30204 Oncology

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 7.100 v roce 2024

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14110/25:00142810

Organizační jednotka

Lékařská fakulta

Klíčová slova anglicky

Endometrial cancer; Risk estimation; Lymph node metastasis; Bayesian network; Molecular classification; Myometrial invasion

Štítky

14110230, 14110240, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 4. 12. 2025 12:59, Mgr. Tereza Miškechová

Anotace

V originále

Background: ENDORISK is a Bayesian network that can assist in preoperative risk estimation of lymph node metastasis (LNM) risk in endometrial cancer (EC) with consistent performance in external validations. To reflect state of the art care, ENDORISK was optimized by integrating molecular classification and preoperative assessment of myometrial invasion (MI). Methods: Variables for POLE, MSI, and preoperative assessment of MI, either by expert transvaginal ultrasound or pelvic magnetic resonance imaging (MRI), were added to develop ENDORISK-2. The p53 biomarker, part of the molecular classification, was already included in ENDORISK. External validation of ENDORISK-2 for LNM pre-diction was performed in two independent cohorts from: Brno (CZ), (n = 581) and T & uuml;bingen (DE), (n = 247). Findings: ENDORISK-2 yielded AUCs of 0.85 (95 % CI 0.80-0.90) (CZ) and 0.86 (95 % CI 0.77-0.96) (DE) for predicting LNM. In patients with low-grade histology, 83 % (CZ) and 89 % (DE) were estimated having less than 10 % risk of LNM, with false negative rates (FNR) of 4.3 % (CZ) and 2.2 % (DE). The previously defined set of minimally required variables, i.e.: preoperative tumor grade, three of the four immunohistochemical (IHC) markers, and one clinical marker, could be interchanged with the new variables, with comparable validation metrics, including AUC values of 0.79-0.87 for LNM prediction. Interpretation. Incorporation of molecular data and preoperative MI improved the flexibility of ENDORISK with comparable diagnostic accuracy for estimating LNM as when based on low-cost immunohistochemical bio-markers. In addition, the high diagnostic accuracy in patients with low-grade EC demonstrates how ENDORISK-2 could aid clinicians in identifying patients in whom surgical lymph node assessment may safely be omitted. These results underline its power for clinical use in both high and low resource countries.

Citovat

LOMBAERS, Marike S; Casper REIJNEN; Ally SPRIK; Petra BRETOVÁ; Marcel GRUBE; Stephanie VREDE; Hege F BERG; Jasmin ASBERGER; Eva COLAS; Jitka HAUSNEROVÁ; Jutta HUVILA; Antonio GIL-MORENO; Xavier MATIAS-GUIU; Michiel SIMONS; Marc P L M SNIJDERS; Nicole C M VISSER; Stefan KOMMOSS; Vít WEINBERGER; Frederic AMANT; Peter BRONSERT; Ingfrid S HALDORSEN; Martin KOSKAS; Camilla KRAKSTAD; Heidi V N KUSTERS-VANDEVELDE; Gemma MANCEBO; Louis J M VAN DER PUTTEN; De La Calle IRENE; Peter J F LUCAS; Arjen HOMMERSOM a Johanna M A PIJNENBORG. ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment. European Journal of Cancer. London: ELSEVIER, 2025, roč. 231, December 2025, s. 1-10. ISSN 0959-8049. Dostupné z: https://doi.org/10.1016/j.ejca.2025.116058.

@article{2537905,
   author = {Lombaers, Marike S and Reijnen, Casper and Sprik, Ally and Bretová, Petra and Grube, Marcel and Vrede, Stephanie and Berg, Hege F and Asberger, Jasmin and Colas, Eva and Hausnerová, Jitka and Huvila, Jutta and GilandMoreno, Antonio and MatiasandGuiu, Xavier and Simons, Michiel and Snijders, Marc P L M and Visser, Nicole C M and Kommoss, Stefan and Weinberger, Vít and Amant, Frederic and Bronsert, Peter and Haldorsen, Ingfrid S and Koskas, Martin and Krakstad, Camilla and KustersandVandevelde, Heidi V N and Mancebo, Gemma and Van Der Putten, Louis J M and Irene, De La Calle and Lucas, Peter J F and Hommersom, Arjen and Pijnenborg, Johanna M A},
   article_location = {London},
   article_number = {December 2025},
   doi = {https://doi.org/10.1016/j.ejca.2025.116058},
   keywords = {Endometrial cancer; Risk estimation; Lymph node metastasis; Bayesian network; Molecular classification; Myometrial invasion},
   language = {eng},
   issn = {0959-8049},
   journal = {European Journal of Cancer},
   title = {ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment},
   url = {https://www.sciencedirect.com/science/article/pii/S095980492500944X?pes=vor&utm_source=clarivate&getft_integrator=clarivate},
   volume = {231},
   year = {2025}
}

TY  - JOUR
ID  - 2537905
AU  - Lombaers, Marike S - Reijnen, Casper - Sprik, Ally - Bretová, Petra - Grube, Marcel - Vrede, Stephanie - Berg, Hege F - Asberger, Jasmin - Colas, Eva - Hausnerová, Jitka - Huvila, Jutta - Gil-Moreno, Antonio - Matias-Guiu, Xavier - Simons, Michiel - Snijders, Marc P L M - Visser, Nicole C M - Kommoss, Stefan - Weinberger, Vít - Amant, Frederic - Bronsert, Peter - Haldorsen, Ingfrid S - Koskas, Martin - Krakstad, Camilla - Kusters-Vandevelde, Heidi V N - Mancebo, Gemma - Van Der Putten, Louis J M - Irene, De La Calle - Lucas, Peter J F - Hommersom, Arjen - Pijnenborg, Johanna M A
PY  - 2025
TI  - ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment
JF  - European Journal of Cancer
VL  - 231
IS  - December 2025
SP  - 1-10
EP  - 1-10
PB  - ELSEVIER
SN  - 09598049
KW  - Endometrial cancer
KW  - Risk estimation
KW  - Lymph node metastasis
KW  - Bayesian network
KW  - Molecular classification
KW  - Myometrial invasion
UR  - https://www.sciencedirect.com/science/article/pii/S095980492500944X?pes=vor&utm_source=clarivate&getft_integrator=clarivate
N2  - Background: ENDORISK is a Bayesian network that can assist in preoperative risk estimation of lymph node metastasis (LNM) risk in endometrial cancer (EC) with consistent performance in external validations. To reflect state of the art care, ENDORISK was optimized by integrating molecular classification and preoperative assessment of myometrial invasion (MI). Methods: Variables for POLE, MSI, and preoperative assessment of MI, either by expert transvaginal ultrasound or pelvic magnetic resonance imaging (MRI), were added to develop ENDORISK-2. The p53 biomarker, part of the molecular classification, was already included in ENDORISK. External validation of ENDORISK-2 for LNM pre-diction was performed in two independent cohorts from: Brno (CZ), (n = 581) and T & uuml;bingen (DE), (n = 247). Findings: ENDORISK-2 yielded AUCs of 0.85 (95 % CI 0.80-0.90) (CZ) and 0.86 (95 % CI 0.77-0.96) (DE) for predicting LNM. In patients with low-grade histology, 83 % (CZ) and 89 % (DE) were estimated having less than 10 % risk of LNM, with false negative rates (FNR) of 4.3 % (CZ) and 2.2 % (DE). The previously defined set of minimally required variables, i.e.: preoperative tumor grade, three of the four immunohistochemical (IHC) markers, and one clinical marker, could be interchanged with the new variables, with comparable validation metrics, including AUC values of 0.79-0.87 for LNM prediction. Interpretation. Incorporation of molecular data and preoperative MI improved the flexibility of ENDORISK with comparable diagnostic accuracy for estimating LNM as when based on low-cost immunohistochemical bio-markers. In addition, the high diagnostic accuracy in patients with low-grade EC demonstrates how ENDORISK-2 could aid clinicians in identifying patients in whom surgical lymph node assessment may safely be omitted. These results underline its power for clinical use in both high and low resource countries.
ER  -

LOMBAERS, Marike S; Casper REIJNEN; Ally SPRIK; Petra BRETOVÁ; Marcel GRUBE; Stephanie VREDE; Hege F BERG; Jasmin ASBERGER; Eva COLAS; Jitka HAUSNEROVÁ; Jutta HUVILA; Antonio GIL-MORENO; Xavier MATIAS-GUIU; Michiel SIMONS; Marc P L M SNIJDERS; Nicole C M VISSER; Stefan KOMMOSS; Vít WEINBERGER; Frederic AMANT; Peter BRONSERT; Ingfrid S HALDORSEN; Martin KOSKAS; Camilla KRAKSTAD; Heidi V N KUSTERS-VANDEVELDE; Gemma MANCEBO; Louis J M VAN DER PUTTEN; De La Calle IRENE; Peter J F LUCAS; Arjen HOMMERSOM a Johanna M A PIJNENBORG. ENDORISK-2: A personalized Bayesian network for preoperative risk stratification in endometrial cancer, integrating molecular classification and preoperative myometrial invasion assessment. \textit{European Journal of Cancer}. London: ELSEVIER, 2025, roč.~231, December 2025, s.~1-10. ISSN~0959-8049. Dostupné z: https://doi.org/10.1016/j.ejca.2025.116058.

Přehled o publikaci