Predicting Factors Affecting the First Recurrence of Epithelial Ovarian Cancer Using Random Survival Forest
Predicting survival time has many Effective implications in life quality management for the remainder of the patient's life. Also, survival data are highly variable and make accurate predictions difficult or impossible. Random Survival Forest by repeated tree construction on Bootstrap samples and averaging on the results of these trees reduce the prediction error and cause further generalization of these results. In this retrospective study, the records of 141 patients with epithelial ovarian cancer who were referred to the oncology and radiotherapy ward of Imam Hossein Hospital in Tehran from 2007 to 2018 were used. Random Survival Forest was fitted to the data to investigate the key factors affecting the first recurrence of epithelial ovarian cancer. The mean age of the patients in our study was 52 (23-82) years and the median time to the first recurrence in these was 17 (0.5-127) months, respectively. According to RSF results, using variable importance criterion (VIMP) metastatic tumor with relative importance 2.665 and also using minimal (MD) by depth 2.349, tumor stage with relative importance 1.993 and depth 2.678, and maximum platelet count with relative importance 2.132 and depth 2.683 were the most important variables affecting in the first recurrence of Epithelial Ovarian Cancer. One of the disadvantages of classical methods is the inappropriate fitting of many variables and the need for specific assumptions. More advanced methods such as RSF without the need for any specific assumptions with less prediction error can well explain event variations when exposed to high-dimensional data.
2. Paik ES, Lee J-W, Park J-Y, Kim J-H, Kim M, Kim T-J, et al. Prediction of survival outcomes in patients with epithelial ovarian cancer using machine learning methods. J Gynecol Oncol 2019; 30: e65.
3. Lipson R. Predicting Ovarian Cancer Survival Times: Performance of Parametric Methods and Random Survival Forests [dissertation]. Canada: Simon Fraser University., 2014.
4. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. Ann Appl Stat 2008;2:841-60.
5. Okunade KS, Adetuyi IE, Adenekan M, Ohazurike E, Anorlu RI. Risk predictors of early recurrence in women with epithelial ovarian cancer in Lagos, Nigeria. Pan Afr Med J 2020;36:272.
6. Xiaoyan L. Risk factors of epithelial ovarian cancer recurrence. Modern Oncol 2016;24:2283-5.
7. Ditto A, Leone Roberti Maggiore U, Bogani G, Martinelli F, Chiappa V, Evangelista MT, et al. Predictive factors of recurrence in patients with early‐stage epithelial ovarian cancer. Int J Obstet Gynecol 2019;145:28-33.
8. Dietrich S. Investigation of the machine learning method Random Survival Forest as an exploratory analysis tool for the identification of variables associated with disease risks in complex survival data [dissertation]. Berlin: University of Berlin., 2016.
9. Ishwaran H, Kogalur UB, Gorodeski EZ, Minn AJ, Lauer MS. High-dimensional variable selection for survival data. J Am Stat Assoc 2010;105:205-17.
10. Deldar M, Anbiaee R, Jalilian A, Sayehmiri K, Azimi S. Comparison of Cox’s Regression Model and Weibull’ Parametric Model in Evaluating Factors Affecting in First Recurrence of Epithelial Ovarian Cancer. Acta Med Iran 2020;58:445-51
11. Siroky DS. Navigating random forests and related advances in algorithmic modeling. Stat Surv 2009;3:147-63.
12. van der Schaaf A, Xu C-J, van Luijk P, van’t Veld AA, Langendijk JA, Schilstra C. Multivariate modeling of complications with data driven variable selection: guarding against overfitting and effects of data set size. Radiother Oncol 2012;105:115-21.
13. Broadhurst DI, Kell DB. Statistical strategies for avoiding false discoveries in metabolomics and related experiments. Metabolomics 2006;2:171-96.
14. Loh WY, Shih YS. Split selection methods for classification trees. Stat Sin 1997;7:815-40.
|Issue||Vol 59, No 8 (2021)|
|Epithelial ovarian cancer First recurrent Random Survival Forest.|
|Rights and permissions|
|This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.|