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 <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.

Biomedical Research Group in Gynecology Vall Hebron Institute of Research Universitat Autònoma de Barcelona CIBERONC Barcelona Spain

Center for Gynecologic Oncology Amsterdam Netherlands Cancer Institute and Amsterdam University Medical Center The Netherlands

Centre for Cancer Biomarkers Department of Clinical Science University of Bergen Bergen Norway

Department for Health Evidence Radboud University Medical Center Nijmegen the Netherlands

Department of Computing Sciences Radboud University Nijmegen The Netherlands

Department of Data Science University of Twente Enschede The Netherlands

Department of Gynecology and Obstetrics University Hospital in Brno and Masaryk University Brno Czech Republic

Department of Internal Medicine Hematology and Oncology University Hospital Brno and Masaryk University Brno Czech Republic

Department of Obstetrics and Gynaecology Canisius Wilhelmina Hospital Nijmegen The Netherlands

Department of Obstetrics and Gynaecology Radboud University Medical Center Nijmegen The Netherlands

Department of Obstetrics and Gynecology Haukeland University Hospital Bergen Norway

Department of Obstetrics and Gynecology Hospital del Mar PSMAR Barcelona Spain

Department of Obstetrics and Gynecology University Medical Center Freiburg Germany

Department of Oncology KU Leuven Leuven Belgium

Department of Pathology and Molecular Genetics and Research Laboratory Hospital Universitari Arnau de Vilanova University of Lleida IRBLleida CIBERONC Lleida Spain

Department of Pathology Canisius Wilhelmina Hospital Nijmegen The Netherlands

Department of Pathology Elisabeth TweeSteden Hospital Tilburg The Netherlands

Department of Pathology Ghent University Hospital Cancer Research Institute Ghent Ghent Belgium

Department of Pathology Radboud University Medical Center Nijmegen The Netherlands

Department of Pathology University Hospital Brno and Masaryk University Brno Czech Republic

Department of Pathology University of Turku Turku Finland

Gynecological Department Vall Hebron University Hospital CIBERONC Barcelona Spain

Institute of Pathology University Medical Center Freiburg Germany

Institute of Veterinary Medicine Georg August University Goettingen Germany

Mohn Medical Imaging and Visualization Centre Department of Radiology Haukeland University Hospital Bergen Norway

Obstetrics and Gynecology Department Bichat Claude Bernard Hospital Paris France

Pathology Department Vall Hebron University Hospital CIBERONC Barcelona Spain

Zobrazit více v PubMed

Lucas PJ, van der Gaag LC, Abu-Hanna A. Bayesian networks in biomedicine and health-care. Artif Intell Med. 2004;30(3):201–14. 10.1016/j.artmed.2003.11.001 . PubMed DOI

Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68(6):394–424. 10.3322/caac.21492 . PubMed DOI

Matei D, Filiaci V, Randall ME, Mutch D, Steinhoff MM, DiSilvestro PA, et al. Adjuvant Chemotherapy plus Radiation for Locally Advanced Endometrial Cancer. N Engl J Med. 2019;380(24):2317–26. 10.1056/NEJMoa1813181 PubMed DOI PMC

de Boer SM, Powell ME, Mileshkin L, Katsaros D, Bessette P, Haie-Meder C, et al. Adjuvant chemoradiotherapy versus radiotherapy alone in women with high-risk endometrial cancer (PORTEC-3): patterns of recurrence and post-hoc survival analysis of a randomised phase 3 trial. Lancet Oncol. 2019;20(9):1273–1285. 10.1016/S1470-2045(19)30395-X . PubMed DOI PMC

Frost JA, Webster KE, Bryant A, Morrison J. Lymphadenectomy for the management of endometrial cancer. Cochrane Database Syst Rev. 2017;10:CD007585 10.1002/14651858.CD007585.pub4 PubMed DOI PMC

A Study in the Treatment of Endometrial Cancer study (ASTEC) group, Kitchener H, Swart AM, Qian Q, Amos C, Parmar MK. Efficacy of systematic pelvic lymphadenectomy in endometrial cancer (MRC ASTEC trial): a randomised study. Lancet. 2009;373(9658):125–36. Epub 2008/12/16. 10.1016/S0140-6736(08)61766-3 PubMed DOI PMC

Colombo N, Creutzberg C, Amant F, Bosse T, Gonzalez-Martin A, Ledermann J, et al. ESMO-ESGO-ESTRO Consensus Conference on Endometrial Cancer: diagnosis, treatment and follow-up. Ann Oncol. 2016;27(1):16–41. Epub 2015/12/02. 10.1093/annonc/mdv484 . PubMed DOI

Trovik J, Wik E, Werner HM, Krakstad C, Helland H, Vandenput I, et al. Hormone receptor loss in endometrial carcinoma curettage predicts lymph node metastasis and poor outcome in prospective multicentre trial. Eur J Cancer. 2013;49(16):3431–41. 10.1016/j.ejca.2013.06.016 . PubMed DOI

Bendifallah S, Canlorbe G, Collinet P, Arsene E, Huguet F, Coutant C, et al. Just how accurate are the major risk stratification systems for early-stage endometrial 10.1038/bjc.2015.35 Br J Cancer. 2015;112(5):793–801. PubMed Central PMCID: PMC4453957. PubMed DOI PMC

Wissing M, Mitric C, Amajoud Z, Abitbol J, Yasmeen A, Lopez-Ozuna V, et al. Risk factors for lymph nodes involvement in obese women with endometrial carcinomas. Gynecol Oncol. 2019;155(1):27–33. 10.1016/j.ygyno.2019.07.016 . PubMed DOI

Kang S, Kang WD, Chung HH, Jeong DH, Seo SS, Lee JM, et al. Preoperative identification of a low-risk group for lymph node metastasis in endometrial cancer: a Korean gynecologic oncology group study. J Clin Oncol. 2012;30(12):1329–34. 10.1200/JCO.2011.38.2416 . PubMed DOI

Todo Y, Sakuragi N, Nishida R, Yamada T, Ebina Y, Yamamoto R, et al. Combined use of magnetic resonance imaging, CA 125 assay, histologic type, and histologic grade in the prediction of lymph node metastasis in endometrial carcinoma. Am J Obstet Gynecol. 2003;188(5):1265–72. 10.1067/mob.2003.318 . PubMed DOI

Lee JY, Jung DC, Park SH, Lim MC, Seo SS, Park SY, et al. Preoperative prediction model of lymph node metastasis in endometrial cancer. Int J Gynecol Cancer. 2010;20(8):1350–5. 10.1111/IGC.0b013e3181f44f5a . PubMed DOI

Koskas M, Fournier M, Vanderstraeten A, Walker F, Timmerman D, Vergote I, et al. Evaluation of models to predict lymph node metastasis in endometrial cancer: A multicentre study. Eur J Cancer. 2016;61:52–60. 10.1016/j.ejca.2016.03.079 . PubMed DOI

Cancer Genome Atlas Research N, Kandoth C, Schultz N, Cherniack AD, Akbani R, Liu Y, et al. Integrated genomic characterization of endometrial carcinoma. Nature. 2013;497(7447):67–73. 10.1038/nature12113 PubMed DOI PMC

van der Putten LJ, Visser NC, van de Vijver K, Santacana M, Bronsert P, Bulten J, et al. L1CAM expression in endometrial carcinomas: an ENITEC collaboration study. Br J Cancer. 2016;115(6):716–24. 10.1038/bjc.2016.235 PubMed DOI PMC

Raffone A, Travaglino A, Mascolo M, Carbone L, Guida M, Insabato L, et al. TCGA molecular groups of endometrial cancer: Pooled data about prognosis. Gynecol Oncol. 2019;155(2):374–383. 10.1016/j.ygyno.2019.08.019 . PubMed DOI

Reijnen C, IntHout J, Massuger L, Strobbe F, Kusters-Vandevelde HVN, Haldorsen IS, et al. Diagnostic Accuracy of Clinical Biomarkers for Preoperative Prediction of Lymph Node Metastasis in Endometrial Carcinoma: A Systematic Review and Meta-Analysis. Oncologist. 2019;24(9):e880–e90. 10.1634/theoncologist.2019-0117 PubMed DOI PMC

Wik E, Raeder MB, Krakstad C, Trovik J, Birkeland E, Hoivik EA, et al. Lack of estrogen receptor-alpha is associated with epithelial-mesenchymal transition and PI3K alterations in endometrial carcinoma. Clin Cancer Res. 2013;19(5):1094–105. 10.1158/1078-0432.CCR-12-3039 . PubMed DOI

Huszar M, Pfeifer M, Schirmer U, Kiefel H, Konecny GE, Ben-Arie A, et al. Up-regulation of L1CAM is linked to loss of hormone receptors and E-cadherin in aggressive subtypes of endometrial carcinomas. J Pathol. 2010;220(5):551–61. 10.1002/path.2673 . PubMed DOI

Amirkhani H, Rahmati M, Lucas PJF, Hommersom A. Exploiting Experts' Knowledge for Structure Learning of Bayesian Networks. IEEE Trans Pattern Anal Mach Intell. 2017;39(11):2154–70. 10.1109/TPAMI.2016.2636828 . PubMed DOI

Visser NC, Bulten J, van der Wurff AA, Boss EA, Bronkhorst CM, Feijen HW, et al. PIpelle Prospective ENDOmetrial carcinoma (PIPENDO) study, pre-operative recognition of high risk endometrial carcinoma: a multicentre prospective cohort study. BMC Cancer. 2015;15:487 10.1186/s12885-015-1487-3 PubMed DOI PMC

Kommoss FK, Karnezis AN, Kommoss F, Talhouk A, Taran FA, Staebler A, et al. L1CAM further stratifies endometrial carcinoma patients with no specific molecular risk profile. Br J Cancer. 2018;119(4):480–6. 10.1038/s41416-018-0187-6 PubMed DOI PMC

Bodurtha Smith AJ, Fader AN, Tanner EJ. Sentinel lymph node assessment in endometrial cancer: a systematic review and meta-analysis. Am J Obstet Gynecol. 2017;216(5):459–76 e10. Epub 2016/11/18. 10.1016/j.ajog.2016.11.1033 . PubMed DOI

Holloway RW, Abu-Rustum NR, Backes FJ, Boggess JF, Gotlieb WH, Jeffrey Lowery W, et al. Sentinel lymph node mapping and staging in endometrial cancer: A Society of Gynecologic Oncology literature review with consensus recommendations. Gynecol Oncol. 2017;146(2):405–15. 10.1016/j.ygyno.2017.05.027 PubMed DOI PMC

Schiavone MB, Scelzo C, Straight C, Zhou Q, Alektiar KM, Makker V, et al. Survival of Patients with Serous Uterine Carcinoma Undergoing Sentinel Lymph Node Mapping. Ann Surg Oncol. 2017;24(7):1965–71. Epub 2017/03/05. 10.1245/s10434-017-5816-4 PubMed DOI PMC

Chan JK, Cheung MK, Huh WK, Osann K, Husain A, Teng NN, et al. Therapeutic role of lymph node resection in endometrioid corpus cancer: a study of 12,333 patients. Cancer. 2006;107(8):1823–30. 10.1002/cncr.22185 . PubMed DOI

Preoperative CA125 Significantly Improves Risk Stratification in High-Grade Endometrial Cancer

External validation study of endometrial cancer preoperative risk stratification model (ENDORISK)

The Clinical Significance of DJ1 and L1CAM Serum Level Monitoring in Patients with Endometrial Cancer