國立虎尾科技大學 |

Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data./
作者:	Humphrey, Kyle.
面頁冊數:	1 online resource (49 pages)
附註:	Source: Masters Abstracts International, Volume: 56-04.
Contained By:	Masters Abstracts International56-04(E).
標題:	Biostatistics. -
電子資源:	click for full text (PQDT)
ISBN:	9781369827217

Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data.
Humphrey, Kyle.

Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data. - 1 online resource (49 pages)

Source: Masters Abstracts International, Volume: 56-04.

Thesis (M.S.)--The University of Arizona, 2017.

Includes bibliographical references

In a simulation of an advanced generic cancer trial, I use Q-learning, a reinforcement learning algorithm, to develop dynamic treatment regimes for a continuous treatment, the dose of a single drug. Selected dynamic treatment regimes are tailored to time-varying patient characteristics and to patient subgroups with differential treatment effects. This approach allows estimation of optimal dynamic treatment regimes without a model of the disease process or a priori hypotheses about subgroup membership. Using observed patient characteristics and outcomes from the simulated trial, I estimate Q-functions based on 1) a single regression tree grown by the Classification And Regression Trees (CART) method, 2) random forests, and 3) a slightly modified version of Multivariate Adaptive Regression Splines (MARS). I then compare the survival times of an independent group of simulated patients under treatment regimes estimated using Q-learning with each of the three methods, 10 constant dose regimes, and the best possible treatment regime chosen using a brute force search over all possible treatment regimes with complete knowledge of disease processes and their effects on survival. I also make these comparisons in scenarios with and without spurious high dimensional covariates and with and without patient subgroups with differential treatment effects. Treatment regimes estimated using Q-learning with MARS and random forests greatly increased survival times when compared to the constant dose regimes, but were still considerably lower than the best possible dose regime. Q-learning with a single regression tree did not outperform the constant dose regimes. These results hold across high dimensional and subgroup scenarios. While the MARS method employed produces much more interpretable models than random forests, and therefore has more promise for patient subgroup identification, I show that it is also more sensitive to variations in training data.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369827217Subjects--Topical Terms:

783654
Biostatistics.
Index Terms--Genre/Form:

554714
Electronic books.

Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data.
LDR:03185ntm a2200325Ki 4500 001 918628
005 20181030085011.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369827217
035 $a (MiAaPQ)AAI10282783
035 $a (MiAaPQ)arizona:15579
035 $a AAI10282783
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Humphrey, Kyle. $3 1192996
245 1 0 $a Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data.
264 0 $c 2017
300 $a 1 online resource (49 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: Masters Abstracts International, Volume: 56-04.
500 $a Adviser: Jin Zhou.
502 $a Thesis (M.S.)--The University of Arizona, 2017.
504 $a Includes bibliographical references
520 $a In a simulation of an advanced generic cancer trial, I use Q-learning, a reinforcement learning algorithm, to develop dynamic treatment regimes for a continuous treatment, the dose of a single drug. Selected dynamic treatment regimes are tailored to time-varying patient characteristics and to patient subgroups with differential treatment effects. This approach allows estimation of optimal dynamic treatment regimes without a model of the disease process or a priori hypotheses about subgroup membership. Using observed patient characteristics and outcomes from the simulated trial, I estimate Q-functions based on 1) a single regression tree grown by the Classification And Regression Trees (CART) method, 2) random forests, and 3) a slightly modified version of Multivariate Adaptive Regression Splines (MARS). I then compare the survival times of an independent group of simulated patients under treatment regimes estimated using Q-learning with each of the three methods, 10 constant dose regimes, and the best possible treatment regime chosen using a brute force search over all possible treatment regimes with complete knowledge of disease processes and their effects on survival. I also make these comparisons in scenarios with and without spurious high dimensional covariates and with and without patient subgroups with differential treatment effects. Treatment regimes estimated using Q-learning with MARS and random forests greatly increased survival times when compared to the constant dose regimes, but were still considerably lower than the best possible dose regime. Q-learning with a single regression tree did not outperform the constant dose regimes. These results hold across high dimensional and subgroup scenarios. While the MARS method employed produces much more interpretable models than random forests, and therefore has more promise for patient subgroup identification, I show that it is also more sensitive to variations in training data.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Biostatistics. $3 783654
655 7 $a Electronic books. $2 local $3 554714
690 $a 0308
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Arizona. $b Biostatistics. $3 1192997
773 0 $t Masters Abstracts International $g 56-04(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10282783 $z click for full text (PQDT)