Integrating real-world data and machine learning: A framework to assess covariate importance in real-world use of alternative intravenous dosing regimens for atezolizumab

IF 3.1 3区 医学 Q2 MEDICINE, RESEARCH & EXPERIMENTAL Cts-Clinical and Translational Science Pub Date : 2024-11-18 DOI:10.1111/cts.70077
Bianca Vora, Ashutosh Jindal, Erick Velasquez, James Lu, Benjamin Wu
{"title":"Integrating real-world data and machine learning: A framework to assess covariate importance in real-world use of alternative intravenous dosing regimens for atezolizumab","authors":"Bianca Vora,&nbsp;Ashutosh Jindal,&nbsp;Erick Velasquez,&nbsp;James Lu,&nbsp;Benjamin Wu","doi":"10.1111/cts.70077","DOIUrl":null,"url":null,"abstract":"<p>The increase in the availability of real-world data (RWD), in combination with advances in machine learning (ML) methods, provides a unique opportunity for the integration of the two to explore complex clinical pharmacology questions. Here we present a recently developed RWD/ML framework that utilizes ML algorithms to understand the influence and importance of various covariates on the use of a given dose and schedule for drugs that have multiple approved dosing regimens. To demonstrate the application of this framework, we present atezolizumab as a use case on account of its three approved alternative intravenous (IV) dosing regimens. As expected, the real-world use of atezolizumab has generally been increasing since 2016 for the 1200 mg every 3 weeks regimen and since 2019 for the 1680 mg every 4 weeks regimen. Out of the ML algorithms evaluated, XGBoost performed the best, as measured by the area under the precision–recall curve, with an emphasis on the under-sampled class given the imbalance in the data. The importance of features was measured by Shapley Additive exPlanations (SHAP) values and showed metastatic breast cancer and use of protein-bound paclitaxel as the most correlated with the use of 840 mg every 2 weeks. Although patient usage data for alternative IV dosing regimens are still maturing, these analyses provide initial insights on the use of atezolizumab and set up a framework for the re-analysis of atezolizumab (at a future data cut) as well as application to other molecules with approved alternative dosing regimens.</p>","PeriodicalId":50610,"journal":{"name":"Cts-Clinical and Translational Science","volume":"17 11","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cts.70077","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cts-Clinical and Translational Science","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cts.70077","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

The increase in the availability of real-world data (RWD), in combination with advances in machine learning (ML) methods, provides a unique opportunity for the integration of the two to explore complex clinical pharmacology questions. Here we present a recently developed RWD/ML framework that utilizes ML algorithms to understand the influence and importance of various covariates on the use of a given dose and schedule for drugs that have multiple approved dosing regimens. To demonstrate the application of this framework, we present atezolizumab as a use case on account of its three approved alternative intravenous (IV) dosing regimens. As expected, the real-world use of atezolizumab has generally been increasing since 2016 for the 1200 mg every 3 weeks regimen and since 2019 for the 1680 mg every 4 weeks regimen. Out of the ML algorithms evaluated, XGBoost performed the best, as measured by the area under the precision–recall curve, with an emphasis on the under-sampled class given the imbalance in the data. The importance of features was measured by Shapley Additive exPlanations (SHAP) values and showed metastatic breast cancer and use of protein-bound paclitaxel as the most correlated with the use of 840 mg every 2 weeks. Although patient usage data for alternative IV dosing regimens are still maturing, these analyses provide initial insights on the use of atezolizumab and set up a framework for the re-analysis of atezolizumab (at a future data cut) as well as application to other molecules with approved alternative dosing regimens.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
整合真实世界数据和机器学习:评估阿特珠单抗替代静脉给药方案实际使用中协变量重要性的框架
真实世界数据(RWD)可用性的增加与机器学习(ML)方法的进步相结合,为两者的整合提供了一个独特的机会,以探索复杂的临床药理问题。在此,我们介绍最近开发的 RWD/ML 框架,该框架利用 ML 算法来了解各种协变量对使用给定剂量和给药计划的影响和重要性。为了演示该框架的应用,我们将阿特珠单抗作为一个用例,介绍其三种已获批准的静脉注射(IV)给药方案。不出所料,自 2016 年以来,atezolizumab 每 3 周 1200 毫克的给药方案和 2019 年以来每 4 周 1680 毫克的给药方案在现实世界中的使用量普遍增加。在所评估的 ML 算法中,XGBoost 的表现最佳,其衡量标准是精确度-召回曲线下的面积,鉴于数据的不平衡性,其重点是采样不足的类别。特征的重要性通过 Shapley Additive exPlanations(SHAP)值来衡量,结果显示转移性乳腺癌和使用蛋白结合型紫杉醇与每两周使用 840 毫克的相关性最高。尽管替代静脉给药方案的患者使用数据仍在不断成熟,但这些分析提供了关于阿特珠单抗使用情况的初步见解,并为阿特珠单抗的重新分析(在未来数据切分时)以及应用于其他已获批准的替代给药方案的分子建立了框架。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Cts-Clinical and Translational Science
Cts-Clinical and Translational Science 医学-医学:研究与实验
CiteScore
6.70
自引率
2.60%
发文量
234
审稿时长
6-12 weeks
期刊介绍: Clinical and Translational Science (CTS), an official journal of the American Society for Clinical Pharmacology and Therapeutics, highlights original translational medicine research that helps bridge laboratory discoveries with the diagnosis and treatment of human disease. Translational medicine is a multi-faceted discipline with a focus on translational therapeutics. In a broad sense, translational medicine bridges across the discovery, development, regulation, and utilization spectrum. Research may appear as Full Articles, Brief Reports, Commentaries, Phase Forwards (clinical trials), Reviews, or Tutorials. CTS also includes invited didactic content that covers the connections between clinical pharmacology and translational medicine. Best-in-class methodologies and best practices are also welcomed as Tutorials. These additional features provide context for research articles and facilitate understanding for a wide array of individuals interested in clinical and translational science. CTS welcomes high quality, scientifically sound, original manuscripts focused on clinical pharmacology and translational science, including animal, in vitro, in silico, and clinical studies supporting the breadth of drug discovery, development, regulation and clinical use of both traditional drugs and innovative modalities.
期刊最新文献
Use cases of registry-based randomized controlled trials—A review of the registries' contributions and constraints Integrating real-world data and machine learning: A framework to assess covariate importance in real-world use of alternative intravenous dosing regimens for atezolizumab High-dose intranasal insulin in an adaptive dose-escalation study in healthy human participants Accumulation of endogenous Muse cells in the myocardium and its pathophysiological role in patients with fulminant myocarditis A randomized, placebo-controlled first-in-human study of oral TQS-168 in healthy volunteers: Assessment of safety, tolerability, pharmacokinetics, pharmacodynamics, and food effect
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1