scholarly journals Estimating heterogeneous treatment effects by balancing heterogeneity and fitness

2018 ◽  
Author(s):  
Weijia Zhang ◽  
Thuc Le ◽  
Lin Liu ◽  
Jiuyong Li
Keyword(s):  
Treatment Effects ◽  
Recursive Partitioning ◽  
Superior Performance ◽  
Breast Cancer Patients ◽  
Computationally Efficient ◽  
Gene Expressions ◽  
Heterogeneous Treatment Effects ◽  
Multi Objective ◽  
Biological And Medical Applications ◽  
Better Than

AbstractEstimating heterogeneous treatment effects is an important problem in many medical and biological applications since treatments may have different effects on the prognoses of different patients. Recently, several recursive partitioning methods have been proposed to identify the subgroups that with different responds to a treatment, and they rely on a fitness criterion to minimize the error between the estimated treatment effects and the unobservable true effects. In this paper, we propose that a heterogeneity criterion, which maximizes the differences of treatment effects among the subgroups, also needs to be considered. Moreover, we show that better performances can be achieved when the fitness and the heterogeneous criteria are considered simultaneously. Selecting the optimal splitting points then becomes a multi-objective problem; however, a solution that achieves optimal in both aspects are often not available. To solve this problem, we propose a multi-objective splitting procedure to balance both criteria. The proposed procedure is computationally efficient and fits naturally into the existing recursive partitioning framework. Experimental results show that the proposed multi-objective approach performs consistently better than existing ones.Author summaryThe effects of a treatment are often not the same for different individuals with different gene expressions. Learning to predict the heterogeneous treatment effects from clinical and expression data is an important step towards personalized medical treatment. Existing computational methods are not ideal for the task because they do not address the interpretability of the model and do not consider the limited sample sizes in biological and medical applications. Our method addresses these issues and achieves superior performance in analyzing the treatment effects of radiotherapy on breast cancer patients.

Estimating Heterogeneous Treatment Effects and the Effects of Heterogeneous Treatments with Ensemble Methods

2017 ◽  
Vol 25 (4) ◽  
pp. 413-434 ◽  
Author(s):  
Justin Grimmer ◽  
Solomon Messing ◽  
Sean J. Westwood
Keyword(s):  
Treatment Effects ◽  
Ensemble Methods ◽  
Ensemble Method ◽  
Superior Performance ◽  
Accurate Estimation ◽  
Randomized Experiments ◽  
Heterogeneous Treatment Effects ◽  
Data Set ◽  
Heterogeneous Effects ◽  
The Ensemble Method

Randomized experiments are increasingly used to study political phenomena because they can credibly estimate the average effect of a treatment on a population of interest. But political scientists are often interested in how effects vary across subpopulations—heterogeneous treatment effects—and how differences in the content of the treatment affects responses—the response to heterogeneous treatments. Several new methods have been introduced to estimate heterogeneous effects, but it is difficult to know if a method will perform well for a particular data set. Rather than using only one method, we show how an ensemble of methods—weighted averages of estimates from individual models increasingly used in machine learning—accurately measure heterogeneous effects. Building on a large literature on ensemble methods, we show how the weighting of methods can contribute to accurate estimation of heterogeneous treatment effects and demonstrate how pooling models lead to superior performance to individual methods across diverse problems. We apply the ensemble method to two experiments, illuminating how the ensemble method for heterogeneous treatment effects facilitates exploratory analysis of treatment effects.

scholarly journals Learning Triggers for Heterogeneous Treatment Effects

2019 ◽  
Vol 33 ◽  
pp. 5183-5190 ◽  
Author(s):  
Christopher Tran ◽  
Elena Zheleva
Keyword(s):  
Treatment Effects ◽  
Causal Effect ◽  
Individual Characteristics ◽  
Treatment Needs ◽  
Heterogeneous Treatment Effects ◽  
Individual Level ◽  
Multiple Datasets ◽  
Effect Estimation ◽  
Better Than ◽  
Heterogeneous Treatment Effect

The causal effect of a treatment can vary from person to person based on their individual characteristics and predispositions. Mining for patterns of individual-level effect differences, a problem known as heterogeneous treatment effect estimation, has many important applications, from precision medicine to recommender systems. In this paper we define and study a variant of this problem in which an individuallevel threshold in treatment needs to be reached, in order to trigger an effect. One of the main contributions of our work is that we do not only estimate heterogeneous treatment effects with fixed treatments but can also prescribe individualized treatments. We propose a tree-based learning method to find the heterogeneity in the treatment effects. Our experimental results on multiple datasets show that our approach can learn the triggers better than existing approaches.

scholarly journals Injection-rolling nozzle in an imprint system with continuous injection direct rolling for ultra-thin microstructure guide light plate

2021 ◽  
Vol 13 (4) ◽  
pp. 168781402110112
Author(s):  
Yan Lou ◽  
Kewei Chen ◽  
Xiangwei Zhou ◽  
Yanfeng Feng
Keyword(s):  
Flow Velocity ◽  
Superior Performance ◽  
Light Transmittance ◽  
Velocity Difference ◽  
Orthogonal Experiments ◽  
Width Direction ◽  
Direct Rolling ◽  
Simulation Results ◽  
Continuous Injection ◽  
Better Than

A novel Injection-rolling Nozzle (IRN) in an imprint system with continuous injection direct rolling (CIDR) for ultra-thin microstructure polymer guide light plates was developed to achieve uniform flow velocity and temperature at the width direction of the cavity exit. A novel IRN cavity was designed. There are eight of feature parameters of cavity were optimized by orthogonal experiments and numerical simulation. Results show that the flow velocity at the width direction of the IRN outlet can reach uniformity, which is far better than that of traditional cavity. The smallest flow velocity difference and temperature difference was 0.6 mm/s and 0.24 K, respectively. The superior performance of the IRN was verified through a CIDR experiment. Several 0.35-mm thick, 340-mm wide, and 10-m long microstructural Polymethyl Methacrylate (PMMA) guide light plates were manufactured. The average filling rates of the microgrooves with the aspect ratio 1:3 reached above 93%. The average light transmittance is 88%.

scholarly journals Diagnostic potential of hypoxia-induced genes in liquid biopsies of breast cancer patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Carlos Henrique F. Peiró ◽  
Matheus M. Perez ◽  
Glauco S. A. de Aquino ◽  
Jéssica F. A. Encinas ◽  
Luiz Vinícius de A. Sousa ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Glucose Transporter ◽  
Carbonic Anhydrases ◽  
Breast Cancer Patients ◽  
Gene Expressions ◽  
Liquid Biopsies ◽  
Healthy Women ◽  
Diagnostic Potential ◽  
Laboratory Tool

AbstractIn tumor cells, higher expression of glucose transporter proteins (GLUT) and carbonic anhydrases (CAIX) genes is influenced by hypoxia-induced factors (HIF).Thus, we aimed to study the expression profile of these markers in sequential peripheral blood collections performed in breast cancer patients in order to verify their predictive potential in liquid biopsies. Gene expressions were analyzed by qPCR in tumor and blood samples from 125 patients and 25 healthy women. Differential expression was determined by the 2(−ΔCq) method. Expression of HIF-1α and GLUT1 in the blood of breast cancer patients is significantly higher (90–91 and 160–161 fold increased expression, respectively; p < 0.0001) than that found in healthy women. Their diagnostic power was confirmed by ROC curve. CAIX is also more expressed in breast cancer women blood, but its expression was detected only in a few samples. But none of these genes could be considered predictive markers. Therefore, evaluation of the expression of HIF-1α and GLUT1 in blood may be a useful laboratory tool to complement the diagnosis of breast cancer, in addition to being useful for follow-up of patients and of women with a family history of breast cancer.

scholarly journals Elite Exploitation: A Combination of Mathematical Concept and EMO Approach for Multi-Objective Decision Making

Symmetry ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 136
Author(s):  
Wenxiao Li ◽  
Yushui Geng ◽  
Jing Zhao ◽  
Kang Zhang ◽  
Jianxin Liu
Keyword(s):  
Decision Making ◽  
Optimization Problems ◽  
Hybrid Genetic Algorithm ◽  
Decision Makers ◽  
Superior Performance ◽  
Test Problems ◽  
Mathematical Function ◽  
Hyperbolic Tangent ◽  
Nsga Ii ◽  
Multi Objective

This paper explores the combination of a classic mathematical function named “hyperbolic tangent” with a metaheuristic algorithm, and proposes a novel hybrid genetic algorithm called NSGA-II-BnF for multi-objective decision making. Recently, many metaheuristic evolutionary algorithms have been proposed for tackling multi-objective optimization problems (MOPs). These algorithms demonstrate excellent capabilities and offer available solutions to decision makers. However, their convergence performance may be challenged by some MOPs with elaborate Pareto fronts such as CFs, WFGs, and UFs, primarily due to the neglect of diversity. We solve this problem by proposing an algorithm with elite exploitation strategy, which contains two parts: first, we design a biased elite allocation strategy, which allocates computation resources appropriately to elites of the population by crowding distance-based roulette. Second, we propose a self-guided fast individual exploitation approach, which guides elites to generate neighbors by a symmetry exploitation operator, which is based on mathematical hyperbolic tangent function. Furthermore, we designed a mechanism to emphasize the algorithm’s applicability, which allows decision makers to adjust the exploitation intensity with their preferences. We compare our proposed NSGA-II-BnF with four other improved versions of NSGA-II (NSGA-IIconflict, rNSGA-II, RPDNSGA-II, and NSGA-II-SDR) and four competitive and widely-used algorithms (MOEA/D-DE, dMOPSO, SPEA-II, and SMPSO) on 36 test problems (DTLZ1–DTLZ7, WGF1–WFG9, UF1–UF10, and CF1–CF10), and measured using two widely used indicators—inverted generational distance (IGD) and hypervolume (HV). Experiment results demonstrate that NSGA-II-BnF exhibits superior performance to most of the algorithms on all test problems.

Assessment of different selective agar media for enumeration and isolation ofListeriafrom dairy products

1988 ◽  
Vol 55 (4) ◽  
pp. 579-583 ◽  
Author(s):  
Lucas Dominguez ◽  
José Francisco Fernández ◽  
Victor Briones ◽  
José Luis Blanco ◽  
Guillermo Suárez
Keyword(s):  
Dairy Products ◽  
Agar Medium ◽  
Raw Milk ◽  
Superior Performance ◽  
Direct Plating ◽  
Selective Agar ◽  
Natural Microflora ◽  
Agar Media ◽  
The Difference ◽  
Better Than

SummaryDifferent selective agar media were compared for the recovery and isolation of five species ofListeriafrom raw milk and cheese. The selective media examined were Beerens medium, MacBride medium and that described by Dominguezet al.(1984) with 6 mg/1 acriflavine, listeria selective agar medium (LSAM), and LSAM with 12 mg/1 acriflavine (LSAM × 2A); a non-selective yeast glucose Lemco agar was included for comparison. When the difference between listeria and the natural microflora of raw milk and cheese was 102cfu/ml, listeria could be isolated by direct plating on all media tested. When it was lower than 103–104cfu/ml, listeria were isolated by direct plating only on LSAM and LSAM × 2A. When the difference was greater than 104cfu/ml, a previous enrichment was necessary to isolate them. LSAM and LSAM × 2A media performed better than the other media tested for isolating listeria by direct plating and improved their isolation from dairy products. This superior performance was evaluated by the ability of these media to support colony formation of different species ofListeriatested, the easy recognition of these colonies from those formed by other microorganisms and by their capacity to inhibit the natural microflora of these foods.

Sign in / Sign up

Export Citation Format

Share Document