國立高雄大學圖資館 |

Language: English

Back

Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments /Yaga Sara Thomas.
Author:	Thomas, Yaga Sara,
Description:	1 electronic resource (105 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
Notes:	Advisors: Wu, Yunan; Tang, Chuan-Fa; Morcos, Faruck Committee members: Choudhary, Pankaj; Efromovich, Sam .
Contained By:	Dissertations Abstracts International87-06B.
Subject:	Statistics.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32435085
ISBN:	9798265455840

Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments /
Thomas, Yaga Sara,

Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments /Yaga Sara Thomas. - 1 electronic resource (105 pages)

Source: Dissertations Abstracts International, Volume: 87-06, Section: B.

Precision medicine seeks to improve clinical outcomes by tailoring treatment decisions to individual patient characteristics, rather than relying on a one size fits all approach. In many real world applications such as chronic disease management, cancer therapy, or diabetes care, patients may be eligible for multiple treatment options that vary systematically in intensity or dose. These are referred to as ordinal treatments, where the ordering reflects increasing therapeutic aggressiveness. This thesis develops statistical methods for estimating and inferring optimal Individualized Treatment Regimes (ITRs) in such settings, where the number of treatment levels exceeds two and the treatments are naturally ordinal. A smooth, model-free estimation approach is introduced, leveraging a neighboring data duplication strategy that reduces the ordinal problem to a series of binary comparisons. Smoothing ensures differentiability of the objective function, facilitating valid inference and numerical optimization. The effectiveness of the proposed method is demonstrated through simulation studies and an application to a curated subset of real data from the National Health and Nutrition Examination Survey (NHANES) (Centers for Disease Control and Prevention (CDC), 2023), focused on diabetes treatment. The methodology is further extended to incorporate treatment proportion constraints that reflect practical limitations such as cost, availability, or treatment-related risk. Two approaches are considered: a grid search algorithm and a Lagrangian based method, which are conceptually explored and discussed. These contributions offer flexible and robust tools for learning optimal ITRs in ordinal treatment settings, enhancing decision making in constrained precision medicine environments. 

English

ISBN: 9798265455840Subjects--Topical Terms:

182057
Statistics.
Subjects--Index Terms:

Statistical methods

Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments /
LDR:03435nmm a22004453i 4500 001 693813
005 20260511063028.5
006 m o d
007 cr|nu||||||||
008 260819s2025 miu||||||m |||||||eng d
020 $a 9798265455840
035 $a (MiAaPQD)AAI32435085
035 $a (MiAaPQD)0382vireo:3138Thomas
035 $a AAI32435085
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Thomas, Yaga Sara, $e author. $3 1010522
245 1 0 $a Inference on Optimal Treatment Regimes in Precision Medicine With Ordinal Treatments / $c Yaga Sara Thomas.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (105 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
500 $a Advisors: Wu, Yunan; Tang, Chuan-Fa; Morcos, Faruck Committee members: Choudhary, Pankaj; Efromovich, Sam .
502 $b Ph.D. $c The University of Texas at Dallas $d 2025.
520 $a Precision medicine seeks to improve clinical outcomes by tailoring treatment decisions to individual patient characteristics, rather than relying on a one size fits all approach. In many real world applications such as chronic disease management, cancer therapy, or diabetes care, patients may be eligible for multiple treatment options that vary systematically in intensity or dose. These are referred to as ordinal treatments, where the ordering reflects increasing therapeutic aggressiveness. This thesis develops statistical methods for estimating and inferring optimal Individualized Treatment Regimes (ITRs) in such settings, where the number of treatment levels exceeds two and the treatments are naturally ordinal. A smooth, model-free estimation approach is introduced, leveraging a neighboring data duplication strategy that reduces the ordinal problem to a series of binary comparisons. Smoothing ensures differentiability of the objective function, facilitating valid inference and numerical optimization. The effectiveness of the proposed method is demonstrated through simulation studies and an application to a curated subset of real data from the National Health and Nutrition Examination Survey (NHANES) (Centers for Disease Control and Prevention (CDC), 2023), focused on diabetes treatment. The methodology is further extended to incorporate treatment proportion constraints that reflect practical limitations such as cost, availability, or treatment-related risk. Two approaches are considered: a grid search algorithm and a Lagrangian based method, which are conceptually explored and discussed. These contributions offer flexible and robust tools for learning optimal ITRs in ordinal treatment settings, enhancing decision making in constrained precision medicine environments. 
546 $a English
590 $a School code: 0382
650 4 $a Statistics. $3 182057
650 4 $a Medicine. $3 193819
653 $a Statistical methods
653 $a Precision medicine
653 $a Individualized Treatment Regimes
653 $a Lagrangian based method
690 $a 0564
690 $a 0463
710 2 $a The University of Texas at Dallas. $b Statistics. $e degree granting institution. $3 1010523
720 1 $a Wu, Yunan $e degree supervisor.
720 1 $a Tang, Chuan-Fa $e degree supervisor.
720 1 $a Morcos, Faruck $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-06B.
790 $a 0382
791 $a Ph.D.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32435085