Dataset Information

Greedy outcome weighted tree learning of optimal personalized treatment rules.

ABSTRACT: We propose a subgroup identification approach for inferring optimal and interpretable personalized treatment rules with high-dimensional covariates. Our approach is based on a two-step greedy tree algorithm to pursue signals in a high-dimensional space. In the first step, we transform the treatment selection problem into a weighted classification problem that can utilize tree-based methods. In the second step, we adopt a newly proposed tree-based method, known as reinforcement learning trees, to detect features involved in the optimal treatment rules and to construct binary splitting rules. The method is further extended to right censored survival data by using the accelerated failure time model and introducing double weighting to the classification trees. The performance of the proposed method is demonstrated via simulation studies, as well as analyses of the Cancer Cell Line Encyclopedia (CCLE) data and the Tamoxifen breast cancer data.

SUBMITTER: Zhu R

PROVIDER: S-EPMC5378692 | biostudies-literature | 2017 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Greedy outcome weighted tree learning of optimal personalized treatment rules.

Zhu Ruoqing R Zhao Ying-Qi YQ Chen Guanhua G Ma Shuangge S Zhao Hongyu H

Biometrics 20161004 2

We propose a subgroup identification approach for inferring optimal and interpretable personalized treatment rules with high-dimensional covariates. Our approach is based on a two-step greedy tree algorithm to pursue signals in a high-dimensional space. In the first step, we transform the treatment selection problem into a weighted classification problem that can utilize tree-based methods. In the second step, we adopt a newly proposed tree-based method, known as reinforcement learning trees, to ...[more]

PMID: 27704531

Similar Datasets

Project description:Importance:Optimal treatment for traumatic finger amputation is unknown to date. Objective:To use statistical learning methods to estimate evidence-based treatment assignment rules to enhance long-term functional and patient-reported outcomes in patients after traumatic amputation of fingers distal to the metacarpophalangeal joint. Design, Setting, and Participants:This decision analytical model used data from a retrospective cohort study of 338 consenting adult patients who underwent revision amputation or replantation at 19 centers in the United States and Asia from August 1, 2016, to April 12, 2018. Of those, data on 185 patients were included in the primary analysis. Exposures:Treatment with revision amputation or replantation. Main Outcomes and Measures:Outcome measures were hand strength, dexterity, hand-related quality of life, and pain. A tree-based statistical learning method was used to derive clinical decision rules for treatment of traumatic finger amputation. Results:Among 185 study participants (mean [SD] age, 45 [16] years; 156 [84%] male), the median number of fingers amputated per patient was 1 (range, 1-5); 115 amputations (62%) were distal to the proximal interphalangeal joint, and 110 (60%) affected the nondominant hand. On the basis of the tree-based statistical learning estimates, to maximize hand dexterity or to minimize patient-reported pain, replantation was found to be the best strategy. To maximize hand strength, revision amputation was the best strategy for patients with a single-finger amputation but replantation was preferred for all other injury patterns. To maximize patient-reported quality of life, revision amputation was the best approach for patients with dominant hand injuries, and replantation was the best strategy for patients with nondominant hand injuries. Conclusions and Relevance:The findings suggest that the approach to treating traumatic finger amputations varies based on the patient's injury characteristics and functional needs.

Project description:Personalized medicine has received increasing attention among statisticians, computer scientists, and clinical practitioners. A major component of personalized medicine is the estimation of individualized treatment rules (ITRs). Recently, Zhao et al. (2012) proposed outcome weighted learning (OWL) to construct ITRs that directly optimize the clinical outcome. Although OWL opens the door to introducing machine learning techniques to optimal treatment regimes, it still has some problems in performance. (1) The estimated ITR of OWL is affected by a simple shift of the outcome. (2) The rule from OWL tries to keep treatment assignments that subjects actually received. (3) There is no variable selection mechanism with OWL. All of them weaken the finite sample performance of OWL. In this article, we propose a general framework, called Residual Weighted Learning (RWL), to alleviate these problems, and hence to improve finite sample performance. Unlike OWL which weights misclassification errors by clinical outcomes, RWL weights these errors by residuals of the outcome from a regression fit on clinical covariates excluding treatment assignment. We utilize the smoothed ramp loss function in RWL, and provide a difference of convex (d.c.) algorithm to solve the corresponding non-convex optimization problem. By estimating residuals with linear models or generalized linear models, RWL can effectively deal with different types of outcomes, such as continuous, binary and count outcomes. We also propose variable selection methods for linear and nonlinear rules, respectively, to further improve the performance. We show that the resulting estimator of the treatment rule is consistent. We further obtain a rate of convergence for the difference between the expected outcome using the estimated ITR and that of the optimal treatment rule. The performance of the proposed RWL methods is illustrated in simulation studies and in an analysis of cystic fibrosis clinical trial data.

Dataset Information

Greedy outcome weighted tree learning of optimal personalized treatment rules.

Publications

Greedy outcome weighted tree learning of optimal personalized treatment rules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure