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
592P - Treatment patterns and outcomes in patients with advanced non-small cell lung cancer with MET exon 14 skipping alterations in China
Presenter: Hanxiao Chen
Session: Poster Display
Resources:
Abstract
593P - MET TKIs in Asian patients (pts) with MET exon 14 skipping NSCLC: A matching-adjusted indirect comparison (MAIC)
Presenter: E-e Ke
Session: Poster Display
Resources:
Abstract
594P - The treatment pattern and clinical outcome in NSCLC patients with MET alteration: A retrospective real-world analysis in China
Presenter: Yongfeng Yu
Session: Poster Display
Resources:
Abstract
595P - Durable efficacy of zenocutuzumab, a HER2 x HER3 bispecific antibody, in advanced NRG1 fusion-positive (NRG1+) non-small cell lung cancer (NSCLC)
Presenter: Koichi Goto
Session: Poster Display
Resources:
Abstract
596P - Repotrectinib in patients (pts) from Asia and China with ROS1 fusion-positive (ROS1+) non-small cell lung cancer (NSCLC): Results from the phase I/II TRIDENT-1 trial
Presenter: Ross Soo
Session: Poster Display
Resources:
Abstract
597TiP - A phase I/II study to evaluate the safety and anti-tumor activity of JIN-A02 in patients with EGFR TKI-refractory, EGFR-mutant advanced NSCLC
Presenter: Sun Min Lim
Session: Poster Display
Resources:
Abstract
598TiP - Exploration of aumolertinib in first-line treatment for advanced non-small cell lung cancer patients of performance status 3 with EGFR mutations (19del and L858R)
Presenter: Haiyi Deng
Session: Poster Display
Resources:
Abstract
599TiP - A prospective study of savolitinib plus docetaxel in pretreated EGFR/ALK/ROS1/METex14m-wildtype advanced NSCLC patients with MET overexpression (FirstMET)
Presenter: Shuting Zhan
Session: Poster Display
Resources:
Abstract
600TiP - Phase III study of telisotuzumab vedotin (Teliso-V) vs docetaxel in pretreated c-Met overexpressing EGFR wildtype (WT) non-squamous (NSQ) locally advanced/metastatic non-small cell lung cancer (a/mNSCLC)
Presenter: Junko Tanizaki
Session: Poster Display
Resources:
Abstract
601P - Pembrolizumab in patients of Chinese descent with microsatellite instability-high/mismatch repair deficient advanced solid tumors: KEYNOTE-158
Presenter: Xiaohua Wu
Session: Poster Display
Resources:
Abstract