Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model

Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model

Epithelial ovarian cancer patients usually relapse after primary management. We utilized the support vector machine algorithm to develop a model for the chemo-response using the Cancer Cell Line Encyclopedia (CCLE) and validated the model in The Cancer Genome Atlas (TCGA) and the GSE9891 dataset. Fi...

Full description

Saved in:
Bibliographic Details
Published in:Cancers 2019-02, Vol.11 (2), p.270
Main Authors: Lu, Tzu-Pin, Kuo, Kuan-Ting, Chen, Ching-Hsuan, Chang, Ming-Cheng, Lin, Hsiu-Ping, Hu, Yu-Hao, Chiang, Ying-Cheng, Cheng, Wen-Fang, Chen, Chi-An
Format: Article
Language:eng
Subjects:
Accuracy
Biomarkers
Cancer therapies
Chemotherapy
Clinical trials
Datasets
Gene expression
Genomes
Learning algorithms
Machine learning
Medical prognosis
microarray
Ovarian cancer
Prediction models
predictive model
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Epithelial ovarian cancer patients usually relapse after primary management. We utilized the support vector machine algorithm to develop a model for the chemo-response using the Cancer Cell Line Encyclopedia (CCLE) and validated the model in The Cancer Genome Atlas (TCGA) and the GSE9891 dataset. Finally, we evaluated the feasibility of the model using ovarian cancer patients from our institute. The 10-gene predictive model demonstrated that the high response group had a longer recurrence-free survival (RFS) (log-rank test, = 0.015 for TCGA, = 0.013 for GSE9891 and = 0.039 for NTUH) and overall survival (OS) (log-rank test, = 0.002 for TCGA and = 0.016 for NTUH). In a multivariate Cox hazard regression model, the predictive model (HR: 0.644, 95% CI: 0.436⁻0.952, = 0.027) and residual tumor size < 1 cm (HR: 0.312, 95% CI: 0.170⁻0.573, < 0.001) were significant factors for recurrence. The predictive model (HR: 0.511, 95% CI: 0.334⁻0.783, = 0.002) and residual tumor size < 1 cm (HR: 0.252, 95% CI: 0.128⁻0.496, < 0.001) were still significant factors for death. In conclusion, the patients of high response group stratified by the model had good response and favourable prognosis, whereas for the patients of medium to low response groups, introduction of other drugs or clinical trials might be beneficial.
ISSN:2072-6694
2072-6694