Dataset Information

A modified classification tree method for personalized medicine decisions.

ABSTRACT: The tree-based methodology has been widely applied to identify predictors of health outcomes in medical studies. However, the classical tree-based approaches do not pay particular attention to treatment assignment and thus do not consider prediction in the context of treatment received. In recent years, attention has been shifting from average treatment effects to identifying moderators of treatment response, and tree-based approaches to identify subgroups of subjects with enhanced treatment responses are emerging. In this study, we extend and present modifications to one of these approaches (Zhang et al., 2010 [29]) to efficiently identify subgroups of subjects who respond more favorably to one treatment than another based on their baseline characteristics. We extend the algorithm by incorporating an automatic pruning step and propose a measure for assessment of the predictive performance of the constructed tree. We evaluate the proposed method through a simulation study and illustrate the approach using a data set from a clinical trial of treatments for alcohol dependence. This simple and efficient statistical tool can be used for developing algorithms for clinical decision making and personalized treatment for patients based on their characteristics.

SUBMITTER: Tsai WM

PROVIDER: S-EPMC4707681 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A modified classification tree method for personalized medicine decisions.

Tsai Wan-Min WM Zhang Heping H Buta Eugenia E O'Malley Stephanie S Gueorguieva Ralitza R

Statistics and its interface 20160101 2

The tree-based methodology has been widely applied to identify predictors of health outcomes in medical studies. However, the classical tree-based approaches do not pay particular attention to treatment assignment and thus do not consider prediction in the context of treatment received. In recent years, attention has been shifting from average treatment effects to identifying moderators of treatment response, and tree-based approaches to identify subgroups of subjects with enhanced treatment res ...[more]

PMID: 26770292

Similar Datasets

Project description:Objective: To assess the efficiency of the endometrial immune profiling as a method to design personalized care to enhance the pregnancy rate in a large heterogeneous infertile population. We hypothesized that some reproductive failures could be induced by a uterine immune dysregulation which could be identified and corrected with a targeted plan. Design: Prospective cohort study. Setting: Multicentric study. Intervention(s) and Main outcome measure(s): One thousand and seven hundred thirty-eight infertile patients had an immune profiling on a timed endometrial biopsy between 2012 and 2018. This test documented the absence or the presence of an endometrial immune dysregulation and identified its type. In case of dysregulation, a targeted personalized plan was suggested to the treating clinician aiming to supply the anomaly. One year after the test, the clinician was contacted to provide the outcome of the subsequent embryo transfer with the applied suggested plan. Result(s): After testing, 16.5% of the patients showed no endometrial immune dysregulation, 28% had a local immune under-activation, 45% had a local immune over-activation, and 10.5% had a mixed endometrial immune profile. In patients with a history of repeated implantation failures (RIF) or recurrent miscarriages (RM), the pregnancy rate was significantly higher if an endometrial dysregulation was found and the personalized plan applied, compared to the patients with an apparent balanced immune profile (respectively 37.7 and 56% vs. 26.9 and 24%, p < 0.001). In contrast, in good prognosis IVF (in vitro fertilization) subgroup and patients using donor eggs, this difference was not significant between dysregulated and balanced subgroups, but higher pregnancy rates were observed in absence of dysregulation. For patients with immune over-activation, pregnancy rates were significantly higher for patients who had a test of sensitivity, regarding the type of immunotherapy introduced, when compared to the ones who did not (51 vs. 39.9%, p = 0.012). Conclusion(s): Local endometrial immunity appears to be a new and important parameter able to influence the prognosis of pregnancy. Targeted medical care in case of local immune dysregulation resulted in significantly higher pregnancy rates in RIF and RM patients.

Dataset Information

A modified classification tree method for personalized medicine decisions.

Publications

A modified classification tree method for personalized medicine decisions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure