Article Text

Download PDFPDF
266 Models to predict response to hormonal therapy in patients with recurrent or advanced endometrial cancer
  1. Xiaoman Jin1,
  2. Daphne Silvertand1,
  3. Henrica M.j. Werner1,
  4. Johanna M.a. Pijnenborg2,
  5. Roy I. Lalisang1,
  6. Johan Bulten2,
  7. Ane G.z. Eriksson3,
  8. Kristina Lindemann3,
  9. Heleen J. Van Beekhuizen4,
  10. Hans Trum5,
  11. Petronella. O. Witteveen6,
  12. Khadra Galaal7,
  13. Alexandra Van Ginkel8,
  14. Vit Weinberger9,
  15. Sanne Sweegers2,
  16. Camilla Krakstad10,
  17. Willem Jan Van Weelden2,
  18. Rianne Fijten11,
  19. Andrea Romano1,
  20. ENITEC -consortium12
  1. 1Maastricht University Medical Center+, Maastricht, The Netherlands
  2. 2Radboud university medical center, Nijmegen, The Netherlands
  3. 3Oslo University Hospital, Oslo, Norway
  4. 4Erasmus Medical Center Rotterdam, Rotterdam, The Netherlands
  5. 5Netherlands Cancer Institute, Amsterdam, The Netherlands
  6. 6University Medical Center Utrecht, Utrecht, The Netherlands
  7. 7Royal Cornwall Hospital NHS Trust, Truro, UK
  8. 8Rijnstate hospital, Arnhem, The Netherlands
  9. 9Masaryk University and University Hospital Brno, Brno, Czech Republic
  10. 10University of Bergen, Bergen, Norway
  11. 11GROW School for Oncology and Reproduction, Maastricht, The Netherlands
  12. 12ENITEC: European Network Individualised Treatment Endometrial Cancer, Maastricht, The Netherlands


Introduction/Background There is no clear guidance for systemic treatment in patients with advanced/recurrent endometrial cancer (EC). Hormonal therapies can be considered in a palliative setting, yet there is a lack of biomarkers to predict a therapeutic response to the drug. This study aimed to identify effective biomarkers from tumor transcriptomics and develop artificial intelligence (AI) models which can predict the therapeutic response of patients to hormonal drugs.

Methodology The PROMOTE study population was previously described (van Weelden et al, AJOG 2021) and included patients with advanced stage/recurrent EC treated with hormonal drugs. Tumor samples from a total of 61 patients (out of the full cohort of 102 eligible patients) with sufficient isolated RNA were subjected to RNA-seq (Illumina). Patients were grouped according to their response to Clinical Benefit Rate (CBR: complete response, partial response and stable disease) and Response Rate (RR: complete response, partial response) were computed. Univariate analysis based on DESeq2 method and multivariate analysis based on principle component analysis and recursive feature elimination were applied using R Studio.

Results A total of 97 differentially expressed genes were identified for CBR and 16 (10 upregulated and 6 downregulated) showed a fold-change >4; 103 differentially expressed genes were identified for RR with 24 (16 upregulated and 8 downregulated) showing a fold-change higher than 4. Interestingly, genes involved in the steroid hormone metabolism like HSD17B3, AKR1C2 were differentially expressed in relation to response to hormonal drugs. Prediction models were developed either using transcriptomic data only or after combining transcriptomics with clinical features (age, stage, grade etc.). CBR and RR could be predicted with a good accuracy on the training and test data sets.

Conclusion Based on RNA seq data on pretreatment tumor biopsies the response rate to hormonal drugs can be predicted with a good accuracy.

Disclosures None

Statistics from

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.