估计精神病学治疗效果的异质性:因果森林的回顾和指导

IF 2.4 3区 医学 Q2 PSYCHIATRY
Erik Sverdrup, Maria Petukhova, Stefan Wager
{"title":"估计精神病学治疗效果的异质性:因果森林的回顾和指导","authors":"Erik Sverdrup,&nbsp;Maria Petukhova,&nbsp;Stefan Wager","doi":"10.1002/mpr.70015","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Flexible machine learning tools are increasingly used to estimate heterogeneous treatment effects.</p>\n </section>\n \n <section>\n \n <h3> Aims</h3>\n \n <p>This paper gives an accessible tutorial demonstrating the use of the causal forest algorithm, available in the <i>R</i> package <i>grf</i>.</p>\n </section>\n \n <section>\n \n <h3> Summary</h3>\n \n <p>We start with a brief non-technical overview of treatment effect estimation methods, focusing on estimation in observational studies; the same techniques can also be applied in experimental studies. We then discuss the logic of estimating heterogeneous effects using the extension of the random forest algorithm implemented in <i>grf</i>. Finally, we illustrate causal forest by conducting a secondary analysis on the extent to which individual differences in resilience to high combat stress can be measured among US Army soldiers deploying to Afghanistan based on information about these soldiers available prior to deployment. We illustrate simple and interpretable exercises for model selection and evaluation, including targeting operator characteristics curves, Qini curves, area-under-the-curve summaries, and best linear projections.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>A replication script with simulated data is available at https://github.com/grf-labs/grf/tree/master/experiments/ijmpr.</p>\n </section>\n </div>","PeriodicalId":50310,"journal":{"name":"International Journal of Methods in Psychiatric Research","volume":"34 2","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mpr.70015","citationCount":"0","resultStr":"{\"title\":\"Estimating Treatment Effect Heterogeneity in Psychiatry: A Review and Tutorial With Causal Forests\",\"authors\":\"Erik Sverdrup,&nbsp;Maria Petukhova,&nbsp;Stefan Wager\",\"doi\":\"10.1002/mpr.70015\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>Flexible machine learning tools are increasingly used to estimate heterogeneous treatment effects.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Aims</h3>\\n \\n <p>This paper gives an accessible tutorial demonstrating the use of the causal forest algorithm, available in the <i>R</i> package <i>grf</i>.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Summary</h3>\\n \\n <p>We start with a brief non-technical overview of treatment effect estimation methods, focusing on estimation in observational studies; the same techniques can also be applied in experimental studies. We then discuss the logic of estimating heterogeneous effects using the extension of the random forest algorithm implemented in <i>grf</i>. Finally, we illustrate causal forest by conducting a secondary analysis on the extent to which individual differences in resilience to high combat stress can be measured among US Army soldiers deploying to Afghanistan based on information about these soldiers available prior to deployment. We illustrate simple and interpretable exercises for model selection and evaluation, including targeting operator characteristics curves, Qini curves, area-under-the-curve summaries, and best linear projections.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>A replication script with simulated data is available at https://github.com/grf-labs/grf/tree/master/experiments/ijmpr.</p>\\n </section>\\n </div>\",\"PeriodicalId\":50310,\"journal\":{\"name\":\"International Journal of Methods in Psychiatric Research\",\"volume\":\"34 2\",\"pages\":\"\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mpr.70015\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Methods in Psychiatric Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/mpr.70015\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PSYCHIATRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Methods in Psychiatric Research","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mpr.70015","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0

摘要

灵活的机器学习工具越来越多地用于估计异质治疗效果。本文给出了一个可访问的教程,演示了R包grf中因果森林算法的使用。我们首先简要介绍治疗效果估计方法的非技术概述,重点是观察性研究中的估计;同样的技术也可以应用于实验研究。然后,我们讨论了利用grf中实现的随机森林算法的扩展来估计异构效应的逻辑。最后,我们根据部署到阿富汗的美国陆军士兵在部署前可获得的信息,对部署到阿富汗的美国陆军士兵在高战斗压力恢复力方面的个体差异进行了二次分析,从而说明了因果森林。我们举例说明了简单和可解释的模型选择和评估练习,包括目标操作员特征曲线,Qini曲线,曲线下面积总结和最佳线性预测。结果模拟数据的复制脚本可在https://github.com/grf-labs/grf/tree/master/experiments/ijmpr上获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Estimating Treatment Effect Heterogeneity in Psychiatry: A Review and Tutorial With Causal Forests

Estimating Treatment Effect Heterogeneity in Psychiatry: A Review and Tutorial With Causal Forests

Background

Flexible machine learning tools are increasingly used to estimate heterogeneous treatment effects.

Aims

This paper gives an accessible tutorial demonstrating the use of the causal forest algorithm, available in the R package grf.

Summary

We start with a brief non-technical overview of treatment effect estimation methods, focusing on estimation in observational studies; the same techniques can also be applied in experimental studies. We then discuss the logic of estimating heterogeneous effects using the extension of the random forest algorithm implemented in grf. Finally, we illustrate causal forest by conducting a secondary analysis on the extent to which individual differences in resilience to high combat stress can be measured among US Army soldiers deploying to Afghanistan based on information about these soldiers available prior to deployment. We illustrate simple and interpretable exercises for model selection and evaluation, including targeting operator characteristics curves, Qini curves, area-under-the-curve summaries, and best linear projections.

Results

A replication script with simulated data is available at https://github.com/grf-labs/grf/tree/master/experiments/ijmpr.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.20
自引率
6.50%
发文量
48
审稿时长
>12 weeks
期刊介绍: The International Journal of Methods in Psychiatric Research (MPR) publishes high-standard original research of a technical, methodological, experimental and clinical nature, contributing to the theory, methodology, practice and evaluation of mental and behavioural disorders. The journal targets in particular detailed methodological and design papers from major national and international multicentre studies. There is a close working relationship with the US National Institute of Mental Health, the World Health Organisation (WHO) Diagnostic Instruments Committees, as well as several other European and international organisations. MPR aims to publish rapidly articles of highest methodological quality in such areas as epidemiology, biostatistics, generics, psychopharmacology, psychology and the neurosciences. Articles informing about innovative and critical methodological, statistical and clinical issues, including nosology, can be submitted as regular papers and brief reports. Reviews are only occasionally accepted. MPR seeks to monitor, discuss, influence and improve the standards of mental health and behavioral neuroscience research by providing a platform for rapid publication of outstanding contributions. As a quarterly journal MPR is a major source of information and ideas and is an important medium for students, clinicians and researchers in psychiatry, clinical psychology, epidemiology and the allied disciplines in the mental health field.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信