東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Treatment Effect Estimation and Ther...

Li, Ruohong.

FindBook

Google Book

Amazon

博客來

Treatment Effect Estimation and Therapeutic Optimization Using Observational Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Treatment Effect Estimation and Therapeutic Optimization Using Observational Data./
作者:	Li, Ruohong.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	157 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
Contained By:	Dissertations Abstracts International82-12B.
標題:	Biostatistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28416990
ISBN:	9798515233419

Treatment Effect Estimation and Therapeutic Optimization Using Observational Data.
Li, Ruohong.

Treatment Effect Estimation and Therapeutic Optimization Using Observational Data. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 157 p.

Source: Dissertations Abstracts International, Volume: 82-12, Section: B.

Thesis (Ph.D.)--Indiana University - Purdue University Indianapolis, 2021.

This item must not be sold to any third party vendors.

In this dissertation, I address two essential questions of modern therapeutics: (1) to quantify the effects of pharmacological agents as functions of patient's clinical characteristics; (2) to optimize individual treatment regimen in the presence of multiple treatment options. To address the first question, I proposed a unified framework for the estimation of heterogeneous treatment effect Τ (x), which is expressed as a function of the patient characteristics x. The proposed framework not only covers most of the existing advantage-learning methods in the literature, but also enhances the robustness of different learning methods against outliers by allowing the selection of appropriate loss functions. To cope with high-dimensionality in x, I incorporated into the method modern machine learning algorithms including random forests, gradient boosting machines, and neural networks, for a more scalable implementation. To facilitate the wider use of the developed methods, I developed an R package RCATE, which is now posted on Github for public access. For therapeutic optimization, I developed a treatment recommendation system using offline reinforcement learning. Offline reinforcement learning is a type of machine learning method that enables an agent to learn an optimal policy in the absence of an interactive environment, such as those encountered in the analysis of therapeutics data. The recommendation system optimizes long-term reward, while accounting for the safety of treatment regimens. I tested the method using data from the Systolic Blood Pressure Trial (SPRINT), which included multiple years of follow-up data from thousands of patients on many different antihypertensive drugs. Using the SPRINT data, I developed a treatment recommendation system for antihypertensive therapies.

ISBN: 9798515233419Subjects--Topical Terms:

1002712
Biostatistics.
Subjects--Index Terms:

Pharmacological agents

Treatment Effect Estimation and Therapeutic Optimization Using Observational Data.
LDR:03086nmm a2200397 4500 001 2283629
005 20211115071516.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798515233419
035 $a (MiAaPQ)AAI28416990
035 $a AAI28416990
040 $a MiAaPQ $c MiAaPQ
100 1 $a Li, Ruohong. $3 1256555
245 1 0 $a Treatment Effect Estimation and Therapeutic Optimization Using Observational Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 157 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
500 $a Advisor: Tu, Wanzhu;Wang, Honglang.
502 $a Thesis (Ph.D.)--Indiana University - Purdue University Indianapolis, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a In this dissertation, I address two essential questions of modern therapeutics: (1) to quantify the effects of pharmacological agents as functions of patient's clinical characteristics; (2) to optimize individual treatment regimen in the presence of multiple treatment options. To address the first question, I proposed a unified framework for the estimation of heterogeneous treatment effect Τ (x), which is expressed as a function of the patient characteristics x. The proposed framework not only covers most of the existing advantage-learning methods in the literature, but also enhances the robustness of different learning methods against outliers by allowing the selection of appropriate loss functions. To cope with high-dimensionality in x, I incorporated into the method modern machine learning algorithms including random forests, gradient boosting machines, and neural networks, for a more scalable implementation. To facilitate the wider use of the developed methods, I developed an R package RCATE, which is now posted on Github for public access. For therapeutic optimization, I developed a treatment recommendation system using offline reinforcement learning. Offline reinforcement learning is a type of machine learning method that enables an agent to learn an optimal policy in the absence of an interactive environment, such as those encountered in the analysis of therapeutics data. The recommendation system optimizes long-term reward, while accounting for the safety of treatment regimens. I tested the method using data from the Systolic Blood Pressure Trial (SPRINT), which included multiple years of follow-up data from thousands of patients on many different antihypertensive drugs. Using the SPRINT data, I developed a treatment recommendation system for antihypertensive therapies.
590 $a School code: 0104.
650 4 $a Biostatistics. $3 1002712
650 4 $a Therapy. $3 3343697
650 4 $a Artificial intelligence. $3 516317
650 4 $a Health care management. $3 2122906
650 4 $a Information science. $3 554358
653 $a Pharmacological agents
653 $a Drug effects
653 $a Clinical characteristics
653 $a Individualized treatment regimes
653 $a Machine learning
690 $a 0308
690 $a 0212
690 $a 0723
690 $a 0800
690 $a 0769
710 2 $a Indiana University - Purdue University Indianapolis. $b Biostatistics. $3 3562258
773 0 $t Dissertations Abstracts International $g 82-12B.
790 $a 0104
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28416990