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
250P - Impact of adjuvant chemo(radio)therapy in stage I/II testicular seminoma
Presenter: Mahmoud Eleisawy
Session: Poster Display
Resources:
Abstract
251P - LDH isozyme as a prognostic factor for patients with metastatic clear cell renal cell carcinoma (mCRCC)
Presenter: Hayato Takeda
Session: Poster Display
Resources:
Abstract
252P - Risk factors for recurrence after curative nephrectomy in non-metastatic renal cell carcinoma: A retrospective cohort study
Presenter: Kristine Tejada
Session: Poster Display
Resources:
Abstract
253TiP - WUTSUP-02-II-Neo-Dis-Tis: Investigating the efficacy and safety of neoadjuvant tislelizumab plus disitamab vedotin with adjuvant tislelizumab in upper urinary tract carcinoma: A phase II multi-center study
Presenter: Yige Bao
Session: Poster Display
Resources:
Abstract
254TiP - Prospective observational trial of cabozantinib plus nivolumab in Japanese patients with advanced or metastatic renal cell carcinoma: JACUMET trial
Presenter: Yuji Miura
Session: Poster Display
Resources:
Abstract
264P - Interim results from a phase I study of AMG 509 (xaluritamig), a STEAP1 x CD3 XmAb 2+1 immune therapy in patients with metastatic castration-resistant prostate cancer (mCRPC)
Presenter: Chia-Chi Lin
Session: Poster Display
Resources:
Abstract
266P - Clinical application and potential impact of liquid biopsy on the management of Chinese patients with metastatic castration-resistant prostate cancer (mCRPC): A territory-wide prospective analysis
Presenter: Wai Kay Philip Kwong
Session: Poster Display
Resources:
Abstract
267P - Exploring homologous recombination deficiency threshold for predicting response to PARP inhibitor in prostate cancer
Presenter: Diwei Zhao
Session: Poster Display
Resources:
Abstract
268P - Comparisons of on new-onset prostate cancer in type 2 diabetes mellitus exposed to the SGLT2I and DPP4I: A population-based cohort study
Presenter: Hou In Chou
Session: Poster Display
Resources:
Abstract
269P - Prostate cancer harboring low COMT expression correlates with a poor prognosis and response to enzalutamide
Presenter: Shigekatsu Maekawa
Session: Poster Display
Resources:
Abstract