☆ 4.6 Article

Flexible Machine Learning Estimation of Conditional Average Treatment Effects: A Blessing and a Curse

EPIDEMIOLOGY (2023)

Related references

Note: Only part of the references are listed.

Editorial Material Public, Environmental & Occupational Health

Invited Commentary: Demystifying Statistical Inference When Using Machine Learning in Causal Research

Laura B. Balzer et al.

Summary: This article discusses how to obtain valid statistical inference when using machine learning in causal research. The authors recommend using doubly robust estimators, ensemble methods, and sample splitting to reduce bias and improve inference. The study highlights the importance of the Super Learner library and verifies the effects of different methods through simulation experiments.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2023)

Add to Collection

Article Economics

Estimation of Conditional Average Treatment Effects With High-Dimensional Data

Qingliang Fan et al.

Summary: This study proposes new nonparametric estimators for the reduced dimensional conditional average treatment effect function, with the nuisiance functions estimated by machine learning in the first stage and local linear regression in the second stage. The functional limit theory is derived and a uniform inference procedure based on multiplier bootstrap is provided. The empirical application examines the effect of maternal smoking on a baby's birth weight as a function of the mother's age.

JOURNAL OF BUSINESS & ECONOMIC STATISTICS (2022)

Add to Collection

Article Pharmacology & Pharmacy

Clinical Pharmacogenetics Implementation Consortium Guideline for CYP2C19 Genotype and Clopidogrel Therapy: 2022 Update

Craig R. Lee et al.

Summary: CYP2C19 enzyme plays a role in the activation of clopidogrel, and the genotype of CYP2C19 affects the formation of active metabolites of clopidogrel. Thus, using CYP2C19 genotype to guide the use of clopidogrel can reduce the risk of reduced platelet inhibition and major adverse cardiovascular and cerebrovascular events, particularly for intermediate metabolizers.

CLINICAL PHARMACOLOGY & THERAPEUTICS (2022)

Add to Collection

Article Public, Environmental & Occupational Health

Predicting counterfactual risks under hypothetical treatment strategies: an application to HIV

Barbra A. Dickerman et al.

Summary: The article proposes a approach to counterfactual prediction for risk assessment in populations with different distribution of treatment strategies. It evaluates the performance robustness of a prediction algorithm through implementing contrast algorithms and generating counterfactual data, and discusses the challenges of estimating counterfactual risks under specific treatment strategies.

EUROPEAN JOURNAL OF EPIDEMIOLOGY (2022)

Add to Collection

Review Social Sciences, Mathematical Methods

Estimating individual treatment effects using non-parametric regression models: A review

Alberto Caron et al.

Summary: In this paper, the authors examine the problem of estimating heterogeneous treatment effects using non-parametric regression-based methods, and introduce statistical learning tools for conducting causal inference with observational or non-randomized data. They review and develop a taxonomy of existing frameworks for estimating individual treatment effects, and discuss the issue of model selection. The performance of the methods is demonstrated through simulated studies and an empirical analysis.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Stable learning establishes some common ground between causal inference and machine learning

Peng Cui et al.

Summary: Causal inference plays a significant role in improving the stability, explainability, and fairness of predictive modeling in machine learning. Stable learning, as a common ground between causal inference and machine learning, bridges the gap by addressing the source of risk in machine learning models. It offers a more robust approach for high-stakes applications.

NATURE MACHINE INTELLIGENCE (2022)

Add to Collection

Article Pharmacology & Pharmacy

From Real-World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges

Ioana Bica et al.

Summary: Randomized control trials (RCTs) are the gold standard for testing and introducing new drugs, but do not fully describe the heterogeneity in the final intended treatment population. On the other hand, real-world observational data like electronic health records (EHRs) contain extensive clinical information about heterogeneous patients and their responses to treatments. There are significant opportunities and challenges in using machine learning methods to estimate individualized treatment effects and make treatment recommendations based on observational data.

CLINICAL PHARMACOLOGY & THERAPEUTICS (2021)

Add to Collection

Article Economics

Machine learning estimation of heterogeneous causal effects: Empirical Monte Carlo evidence

Michael C. Knaus et al.

Summary: This study investigates the finite-sample performance of causal machine learning estimators for heterogeneous causal effects at different aggregation levels. Four of the considered estimators consistently perform well across all situations, with multiple steps to account for the complexity of causal effects.

ECONOMETRICS JOURNAL (2021)

Add to Collection

Article Public, Environmental & Occupational Health

Assessing Heterogeneity of Treatment Effects in Observational Studies

Sarah E. Robertson et al.

Summary: This study describes methods for assessing heterogeneity of treatment effects in observational studies, comparing the performance of different estimators in finite samples. The methods were applied to data from a specific study to compare the effect of surgery plus medical therapy with medical therapy alone in patients with chronic coronary artery disease.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2021)

Add to Collection

Article Biology

Quasi-oracle estimation of heterogeneous treatment effects

X. Nie et al.

Summary: The article introduces a general two-step algorithm for estimating heterogeneous treatment effects, which is flexible and easy to use, and has several advantages over existing methods, showing promising performance in simulation setups.

BIOMETRIKA (2021)

Add to Collection

Article Public, Environmental & Occupational Health

Thirteen Questions About Using Machine Learning in Causal Research (You Won't Believe the Answer to Number 10!)

Stephen J. Mooney et al.

Summary: Machine learning is increasingly used in health sciences, not only for data-driven prediction but also for embedding within causal analyses to reduce biases. An introduction and orientation provided in a question-and-answer format can help epidemiologists interested in using machine learning techniques to overcome potential bias and maintain rigor. Sample software code is also available to facilitate entry into using these techniques.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2021)

Add to Collection

Editorial Material Public, Environmental & Occupational Health

Invited Commentary: Machine Learning in Causal Inference-How Do I Love Thee? Let Me Count the Ways

Laura B. Balzer et al.

Summary: In this issue of the Journal, the discussion focuses on machine learning as a tool for causal research, emphasizing the importance of a formal framework for both causal and statistical inference in utilizing machine learning to answer causal questions. The article illustrates the potential pitfalls without such a foundation, provides practical recommendations for integrating machine learning into causal analyses in a principled way, and highlights important areas of ongoing work in this field.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2021)

Add to Collection

Article Mathematical & Computational Biology

Learning and confirming a class of treatment responders in clinical trials

Victor B. Talisa et al.

Summary: The study suggests that in clinical trials, identifying a subpopulation with estimated treatment effects that are beneficial and enrolling future study subjects from this subpopulation can improve the chances of success in follow-up trials.

STATISTICS IN MEDICINE (2021)

Add to Collection

Article Public, Environmental & Occupational Health

Reflection on modern methods: when worlds collide-prediction, machine learning and causal inference

Tony Blakely et al.

INTERNATIONAL JOURNAL OF EPIDEMIOLOGY (2020)

Add to Collection

Article Public, Environmental & Occupational Health

Prediction meets causal inference: the role of treatment in clinical prediction models

Nan van Geloven et al.

EUROPEAN JOURNAL OF EPIDEMIOLOGY (2020)

Add to Collection

Article Public, Environmental & Occupational Health

Counterfactual prediction is not only for causal inference

Barbra A. Dickerman et al.

EUROPEAN JOURNAL OF EPIDEMIOLOGY (2020)

Add to Collection

Article Gastroenterology & Hepatology

The association of non-alcoholic fatty liver disease and cardiac structure and function-Framingham Heart Study

Laura S. Chiu et al.

LIVER INTERNATIONAL (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Causal inference and counterfactual prediction in machine learning for actionable healthcare

Mattia Prosperi et al.

NATURE MACHINE INTELLIGENCE (2020)

Add to Collection

Article Multidisciplinary Sciences

Metalearners for estimating heterogeneous treatment effects using machine learning

Soren R. Kunzel et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

Add to Collection

Article Mathematics, Interdisciplinary Applications

Precision Medicine

Michael R. Kosorok et al.

Annual Review of Statistics and Its Application (2019)

Add to Collection

Article Statistics & Probability

GENERALIZED RANDOM FORESTS

Susan Athey et al.

ANNALS OF STATISTICS (2019)

Add to Collection

Review Public, Environmental & Occupational Health

Big Data in Public Health: Terminology, Machine Learning, and Privacy

Stephen J. Mooney et al.

ANNUAL REVIEW OF PUBLIC HEALTH, VOL 39 (2018)

Add to Collection

Article Economics

Double/debiased machine learning for treatment and structural parameters

Victor Chernozhukov et al.

ECONOMETRICS JOURNAL (2018)

Add to Collection

Article Statistics & Probability

Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods

Min Lu et al.

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS (2018)

Add to Collection

Article Statistics & Probability

Estimation and Inference of Heterogeneous Treatment Effects using Random Forests

Stefan Wager et al.

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION (2018)

Add to Collection

Article Mathematical & Computational Biology

Some methods for heterogeneous treatment effect estimation in high dimensions

Scott Powers et al.

STATISTICS IN MEDICINE (2018)

Add to Collection

Article Mathematical & Computational Biology

Comparing methods for estimation of heterogeneous treatment effects using observational data from health care databases

T. Wendling et al.

STATISTICS IN MEDICINE (2018)

Add to Collection

Article Public, Environmental & Occupational Health

Targeted Maximum Likelihood Estimation for Causal Inference in Observational Studies

Megan S. Schuler et al.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2017)

Add to Collection

Article Multidisciplinary Sciences

Recursive partitioning for heterogeneous causal effects

Susan Athey et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2016)

Add to Collection

Review Medicine, General & Internal

The Framingham Heart Study and the epidemiology of cardiovascular disease: a historical perspective

Syed S. Mahmood et al.

LANCET (2014)

Add to Collection

Article Statistics & Probability

ESTIMATING TREATMENT EFFECT HETEROGENEITY IN RANDOMIZED PROGRAM EVALUATION

Kosuke Imai et al.

ANNALS OF APPLIED STATISTICS (2013)

Add to Collection

Article Statistics & Probability

STOCHASTIC COUNTERFACTUALS AND STOCHASTIC SUFFICIENT CAUSES

Tyler J. VanderWeele et al.

STATISTICA SINICA (2012)

Add to Collection

Article Communication

Modeling Heterogeneous Treatment Effects in Survey Experiments with Bayesian Additive Regression Trees

Donald P. Green et al.

PUBLIC OPINION QUARTERLY (2012)

Add to Collection

Article Statistics & Probability

Bayesian Nonparametric Modeling for Causal Inference

Jennifer L. Hill

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS (2011)

Add to Collection

Article Mathematical & Computational Biology

Subgroup identification from randomized clinical trial data

Jared C. Foster et al.

STATISTICS IN MEDICINE (2011)

Add to Collection

Article Public, Environmental & Occupational Health

On the Distinction Between Interaction and Effect Modification

Tyler J. VanderWeele

EPIDEMIOLOGY (2009)

Add to Collection

Editorial Material Public, Environmental & Occupational Health

The Consistency Statement in Causal Inference A Definition or an Assumption?

Stephen R. Cole et al.

EPIDEMIOLOGY (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.