Abstract 310P
Background
This study investigated site-specific differences in clinical factors for recurrence in patients who were newly diagnosed and treated for endometrial cancer. Several machine learning algorithms were adapted to predict the recurrence of patients.
Methods
Electronic medical records’ data were retrieved from January 2006 to December 2018 for patients who were diagnosed with endometrial cancer at the XXX in Korea. Recurrence sites were classified as local, regional, or distant. We employed various machine learning algorithms, including logistic regression models (LR), random forest (RF), support vector machine (SVM) and artificial neural network (ANN), and assessed their prediction performances by cross-validation. Since our problem is an imbalanced multi-classification problem, the average score of AUC (area under curve) for each class obtained from one-vs-rest strategy was used for evaluating each machine learning algorithm.
Results
The data of 611 patients were selected for analysis; there were 20, 12, and 25 local, regional, and distant recurrence, respectively, and 554 patients had no recurrence. Random forest showed the best performance (0.8587) in prediction accuracy. Other algorithms followed with 0.7790 (LR), 0.7398 (ANN) and SVM (0.7119). The most important variables in Random Forest were invasion depth, age and size, in order.
Conclusions
We identified different risk factors specific for each type of recurrence site. Using these risk factors, we suggest that individually tailored adjuvant treatments be introduced for patients.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
217P - Conditional reprogramming of urine-derived bladder cancer cells: A model for precision medicine
Presenter: Yu Dong
Session: Poster Display
Resources:
Abstract
218P - Clinical effectiveness of tislelizumab combined with gemcitabine/cisplatin (GC) versus GC as adjuvant therapy in high-risk muscle-invasive urothelial carcinoma (MIUC): A real-world study
Presenter: xingliang Tan
Session: Poster Display
Resources:
Abstract
219P - Clinical effectiveness of tislelizumab plus TKI as first-line therapy in patients with metastatic renal cell carcinoma (mRCC): A real-world study
Presenter: Pei Dong
Session: Poster Display
Resources:
Abstract
220P - Heterogeneity in tertiary lymphoid structures predicts distinct prognosis and immune microenvironment characterizations of clear cell renal cell carcinoma
Presenter: Wenhao Xu
Session: Poster Display
Resources:
Abstract
221P - Genetic polymorphism of genes encoding cytokines interleukin1 1-alpha and TNF-alpha in non-muscle invasive bladder cancer
Presenter: Anil Kumar
Session: Poster Display
Resources:
Abstract
222P - The association between response to enfortumab vedotin and peripheral neuropathy: A multicenter retrospective study in Japan
Presenter: Nozomi Hayakawa
Session: Poster Display
Resources:
Abstract
223P - Patient and healthcare practitioner preferences for treatments in advanced renal cell carcinoma
Presenter: Niara Oliveira
Session: Poster Display
Resources:
Abstract
224P - WUTSUP-01: Phase II trial of neoadjuvant toripalimab and chemotherapy in locally advanced upper tract urothelial carcinoma
Presenter: Yige Bao
Session: Poster Display
Resources:
Abstract
225P - A novel multianalyte signature for stratifying Indian non-muscle invasive bladder cancer: A single center observational study
Presenter: Hari P S
Session: Poster Display
Resources:
Abstract
226P - Prognosis stratification of immunotherapy by a mutational signature in urothelial carcinoma
Presenter: Xuebing Han
Session: Poster Display
Resources:
Abstract