Scientific publications
Endometrial Cancer Individualised Scoring System (ECISS): A machine learning-based prediction model of endometrial cancer prognosis
Sherif A Shazly 1 , Pluvio J Coronado 2 , Ercan Yılmaz 3 , Rauf Melekoglu 3 , Hanifi Sahin 3 , Luca Giannella 4 , Andrea Ciavattini 4 , Giovanni Delli Carpini 4 , Jacopo Di Giuseppe 4 , Angel Yordanov 5 , Konstantina Karakadieva 5 , Nevena Milenova Nedelcheva 5 , Mariela Vasileva-Slaveva 5 , Juan Luis Alcazar 6 , Enrique Chacon 6 , Nabil Manzour 6 , Julio Vara 6 , Erbil Karaman 7 , Onur Karaaslan 7 , Latif Hacıoğlu 7 , Duygu Korkmaz 7 , Cem Onal 8 , Jure Knez 9 , Federico Ferrari 10 , Esraa M Hosni 11 , Mohamed E Mahmoud 11 , Gena M Elassall 11 , Mohamed S Abdo 11 , Yasmin I Mohamed 11 , Amr S Abdelbadie 12 ; Middle-Eastern College of Obstetricians and Gynaecologists (MCOG) Muti-Center Studies (MCS) office and Artificial Intelligence Unit (AI)
Objective: Establishing a prognostic model for endometrial cancer (EC), that individualizes risk and management plan per patient and disease characteristics.
Methods: this is multicentre retrospective study conducted in 9 European gynaecologic cancer centres. Women with confirmed EC between January 2008 to December 2015 were included. Demographics, disease characteristics, management, and follow-up information were collected. Cancer-specific survival (CSS) and disease-free survival (DFS) at 3 and 5 years comprise the primary outcomes of the study. Machine learning algorithms were applied to patient and disease characteristics. Model I: pre-treatment model. Calculated probability was added to management variables (model II: treatment model), and the second calculated probability was added to perioperative and postoperative variables (model III).
Results: Out of 1,150 women, 1,144 were eligible for 3-year survival analysis and 860 for 5-year survival analysis. Model I, II, and III accuracies of prediction of 5-year CSS were 84.88%/85.47% (in train and test sets), 85.47%/84.88% and 87.35%/86.05%, respectively. Model I predicted 3-year CSS at an accuracy of 91.34%/87.02%. Accuracy of model I, II and III in predicting 5-year DFS were 74.63%/76.72%, 77.03%/76.72%, and 80.61%/77.78%, respectively.
Conclusion: Endometrial Cancer Individualised Scoring System (ECISS) is a novel machine learning tool assessing patient-specific survival probability with high accuracy.
CITATION Int J Gynaecol Obstet. Int J Gynaecol Obstet. 2023 Jun;161(3):760-768. doi: 10.1002/ijgo.14639. Epub 2023 Jan 19.
Our authors
