Eiryo Kawakami1,2,3, Junya Tabata2, Nozomu Yanaihara4, Tetsuo Ishikawa1,2, Keita Koseki1, Yasushi Iida2, Misato Saito2, Hiromi Komazaki2, Jason S Shapiro2, Chihiro Goto2, Yuka Akiyama2, Ryosuke Saito2, Motoaki Saito2, Hirokuni Takano2, Kyosuke Yamada2, Aikou Okamoto2.
Abstract
PURPOSE: We aimed to develop an ovarian cancer-specific predictive framework for clinical stage, histotype, residual tumor burden, and prognosis using machine learning methods based on multiple biomarkers. EXPERIMENTAL
DESIGN: Overall, 334 patients with epithelial ovarian cancer (EOC) and 101 patients with benign ovarian tumors were randomly assigned to "training" and "test" cohorts. Seven supervised machine learning classifiers, including Gradient Boosting Machine (GBM), Support Vector Machine, Random Forest (RF), Conditional RF (CRF), Naïve Bayes, Neural Network, and Elastic Net, were used to derive diagnostic and prognostic information from 32 parameters commonly available from pretreatment peripheral blood tests and age.
RESULTS: Machine learning techniques were superior to conventional regression-based analyses in predicting multiple clinical parameters pertaining to EOC. Ensemble methods combining weak decision trees, such as GBM, RF, and CRF, showed the best performance in EOC prediction. The values for the highest accuracy and area under the ROC curve (AUC) for segregating EOC from benign ovarian tumors with RF were 92.4% and 0.968, respectively. The highest accuracy and AUC for predicting clinical stages with RF were 69.0% and 0.760, respectively. High-grade serous and mucinous histotypes of EOC could be preoperatively predicted with RF. An ordinal RF classifier could distinguish complete resection from others. Unsupervised clustering analysis identified subgroups among early-stage EOC patients with significantly worse survival.
CONCLUSIONS: Machine learning systems can provide critical diagnostic and prognostic prediction for patients with EOC before initial intervention, and the use of predictive algorithms may facilitate personalized treatment options through pretreatment stratification of patients. ©2019 American Association for Cancer Research.
RCT Entities:
PURPOSE: We aimed to develop an ovarian cancer-specific predictive framework for clinical stage, histotype, residual tumor burden, and prognosis using machine learning methods based on multiple biomarkers. EXPERIMENTAL
DESIGN: Overall, 334 patients with epithelial ovarian cancer (EOC) and 101 patients with benign ovarian tumors were randomly assigned to "training" and "test" cohorts. Seven supervised machine learning classifiers, including Gradient Boosting Machine (GBM), Support Vector Machine, Random Forest (RF), Conditional RF (CRF), Naïve Bayes, Neural Network, and Elastic Net, were used to derive diagnostic and prognostic information from 32 parameters commonly available from pretreatment peripheral blood tests and age.
RESULTS: Machine learning techniques were superior to conventional regression-based analyses in predicting multiple clinical parameters pertaining to EOC. Ensemble methods combining weak decision trees, such as GBM, RF, and CRF, showed the best performance in EOC prediction. The values for the highest accuracy and area under the ROC curve (AUC) for segregating EOC from benign ovarian tumors with RF were 92.4% and 0.968, respectively. The highest accuracy and AUC for predicting clinical stages with RF were 69.0% and 0.760, respectively. High-grade serous and mucinous histotypes of EOC could be preoperatively predicted with RF. An ordinal RF classifier could distinguish complete resection from others. Unsupervised clustering analysis identified subgroups among early-stage EOC patients with significantly worse survival.
CONCLUSIONS: Machine learning systems can provide critical diagnostic and prognostic prediction for patients with EOC before initial intervention, and the use of predictive algorithms may facilitate personalized treatment options through pretreatment stratification of patients. ©2019 American Association for Cancer Research.
Entities:
Year: 2019
PMID： 30979733 DOI： 10.1158/1078-0432.CCR-18-3378
Source DB: PubMed Journal: Clin Cancer Res ISSN： 1078-0432 Impact factor: 12.531