You are here

Article Text

Article menu
Download PDFPDF
Poster and E-Posters
03. Endometrial cancer
1133 ECLAI: personalized clinical management of endometrial cancer using liquid biopsy, genomics and artificial intelligence
  1. Sergio Vela Moreno1,2,
  2. Vijayachitra Modhukur1,2,
  3. Carlos Casas-Arozamena3,4,
  4. José Ignacio Klett-Mingo4,
  5. Ankita Lawarde1,2,
  6. Marta Ostrowska-Lesko5,
  7. Ilona Skrabalak6,
  8. Antonio Gil-Moreno7,8,
  9. Miguel Abal3,
  10. Eva Colás7,8,
  11. Marcin Bobinski6,
  12. Camilla Krakstad9,10,
  13. Andres Salumets1,2,11,
  14. Laura Muinelo-Romay3,4 and
  15. Gema Moreno-Bueno12,4
  1. 1Competence Centre on Health Technologies, Tartu, Estonia
  2. 2Department of Obstetrics and Gynecology, Institute of Clinical Medicine, University of Tartu, Tartu, Estonia
  3. 3Translational Medical Oncology Group (Oncomet), Health Research Institute of Santiago de Compostela (IDIS), University Hospital of Santiago de Compostela (SERGAS), Santiago De Compostela, Spain
  4. 4Centro de Investigación Biomédica en Red de Cáncer (CIBERONC), Madrid, Spain
  5. 5Chair and Department of Toxicology, Medical University of Lublin, Lublin, Poland
  6. 61st Chair and Department of Oncological Gynecology and Gynecology, Medical University of Lublin, Lublin, Poland
  7. 7Biomedical Research Group in Gynecology, Vall d’Hebron Research Institute (VHIR), Universitat Autonoma de Barcelona, Barcelona, Spain
  8. 8Gynecology Department, Vall Hebron University Hospital, Barcelona, Spain
  9. 9Centre for Cancer Biomarkers, Department of Clinical Science, University of Bergen, Bergen, Norway
  10. 10Department of Gynecology and Obstetrics, Haukeland University Hospital, Bergen, Norway
  11. 11Division of Obstetrics and Gynecology, Department of Clinical Science, Intervention and Technology, Karolinska Institute and Karolinska University Hospital, Stockholm, Sweden
  12. 12Biochemistry Department, Universidad Autónoma de Madrid (UAM), Instituto de Investigaciones Biomédicas 'Sols-Morreale' (IIBm-CISC); Fundación MD Anderson Internacional (FMDA), Madrid, Spain

Abstract

Introduction/Background Introduction: Endometrial cancer (EC) constitutes the fourth most common cancer among women in Europe, and in recent years its incidence has increased significantly. Despite good prognosis for patients with localized disease, about 20% of patients classified as low-risk at surgery, experience disease recurrence. Unfortunately, the therapeutic options for EC extrauterine disease are currently limited, likely related to the innate intra-tumoral heterogeneity (ITH). Consequently, there is an urgent need to identify more effective treatment options and accurate diagnostic methods to improve risk stratification and patient survival. Our consortium aims to generate an algorithm that combines clinicopathologic and molecular characteristics to accurately predict the risk of recurrence of EC and the therapeutic outcomes in high-risk EC.

Methodology Methodology: More than 300 samples, including both prospective samples (uterine aspirates (UA) or cfDNA by liquid biopsies) and retrospective tissue EC samples, have been characterized using immunohistochemistry and molecular techniques. Clinical data have been collected for all samples. This information has been utilized by machine learning and artificial intelligence strategies for decoding a novel predictive algorithm to better stratify the risk of recurrence of EC.

Results Results: Different bioinformatic tools have been used to analyze 198 UAs and 50 tumor samples so far in order to identify a predictive algorithm. This predictor, named ECLAI (personalized clinical management of Endometrial Cancer using Liquid biopsy, genomics and Artificial Intelligence), integrates the clinicopathologic, genomic and molecular tumor characteristics to better stratify the risk of recurrence of EC. Derived from this study we have identified specific molecular patterns that could help to correctly classify high-risk EC.

Conclusion Conclusions: The combined analysis of genetic alterations, clinicopathological features and liquid biopsy allows better stratification of EC post-surgery risk and represents a useful tool to improve the management of the disease.

Disclosures Marcin Bobinski has the following potential conflict(s) of interest to report:

- Receipt of honoraria or consultation fees by AstraZeneca, GSK

- Stock shareholder: PolTREG, RYVU, Scope Fluidics.

Other authors do not have potential conflict(s) of interest to report.

  • Endometrial Cancer
  • Molecular Classification
  • Uterine Aspirates
  • Liquid biopsy
  • Artificial Intelligence.

https://doi.org/10.1136/ijgc-2024-ESGO.433

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.