Filters








21,254 Hits in 4.5 sec

$\mathbf{Q}$- and $\mathbf{A}$-Learning Methods for Estimating Optimal Dynamic Treatment Regimes

Phillip J. Schulte, Anastasios A. Tsiatis, Eric B. Laber, Marie Davidian
2014 Statistical Science  
Q- and A-learning are two main approaches for this purpose. We provide a detailed account of these methods, study their performance, and illustrate them using data from a depression study.  ...  A dynamic treatment regime is a set of sequential decision rules that operationalizes this process.  ...  SUPPLEMENTARY MATERIAL Supplement to "Q-and A-Learning Methods for Estimating Optimal Dynamic Treatment Regimes" (DOI: 10.1214/13-STS450SUPP; .pdf).  ... 
doi:10.1214/13-sts450 pmid:25620840 pmcid:PMC4300556 fatcat:wbofrw46qrb7jeavcv742l4lze

C-learning: A new classification framework to estimate optimal dynamic treatment regimes

Baqun Zhang, Min Zhang
2017 Biometrics  
We show that identifying the optimal dynamic treatment regime can be recast as a sequential optimization problem and propose a direct sequential optimization method to estimate the optimal treatment regimes  ...  and treatment history to dramatically improves performance, hence enjoying the advantages of both the traditional outcome regression based methods (Q-and A-learning) and the more recent direct optimization  ...  Acknowledgement The authors would like to thank Marie Davidian and Anastasios (Butch) A. Tsiatis for their valuable comments.  ... 
doi:10.1111/biom.12836 pmid:29228509 fatcat:v7fmq375rjdbxlr23sbddec7ri

Interactive Q-Learning for Quantiles

Kristin A. Linn, Eric B. Laber, Leonard A. Stefanski
2017 Journal of the American Statistical Association  
Existing methods for estimating optimal dynamic treatment regimes from data optimize the mean of a response variable. However, the mean may not always be the most appropriate summary of performance.  ...  We first characterize the optimal regime for a probability and quantile using potential outcomes (Rubin, 1974) and two treatment time-points.  ...  Leonard Stefanski acknowledges support from NIH grants R01 CA085848 and P01 CA142538 and NSF grant DMS-0906421.  ... 
doi:10.1080/01621459.2016.1155993 pmid:28890584 pmcid:PMC5586239 fatcat:o2huynvmzrhjjjqntikmlw4znm

Interactive Q-learning for Probabilities and Quantiles [article]

Kristin A. Linn, Eric B. Laber, Leonard A. Stefanski
2015 arXiv   pre-print
Existing methods for estimating optimal dynamic treatment regimes from data optimize the mean of a response variable. However, the mean may not always be the most appropriate summary of performance.  ...  A dynamic treatment regime is a sequence of decision rules in which each decision rule recommends treatment based on features of patient medical history such as past treatments and outcomes.  ...  Existing methods for estimating optimal dynamic treatment regimes from data optimize the mean of a response variable. However, the mean may not always be the most appropriate summary of performance.  ... 
arXiv:1407.3414v2 fatcat:m77s4dplj5dgbbfo5vbqxroxjq

Reinforcement learning in clinical medicine: a method to optimize dynamic treatment regime over time

Zhongheng Zhang, written on behalf of AME Big-Data Clinical Trial Collaborative Group
2019 Annals of Translational Medicine  
Q-learning is among the earliest methods to identify optimal DTR, which fits linear outcome models in a recursive manner.  ...  In the field of statistics, reinforcement learning has been widely investigated, aiming to identify an optimal dynamic treatment regime (DTR).  ...  Q-learning algorithm Q-learning is a temporal difference control algorithm that can be used to estimate optimal dynamic treatment regime from longitudinal clinical data.  ... 
doi:10.21037/atm.2019.06.75 pmid:31475215 pmcid:PMC6694251 fatcat:pywkbaenw5ezhecxroppae5ey4

Use of personalized Dynamic Treatment Regimes (DTRs) and Sequential Multiple Assignment Randomized Trials (SMARTs) in mental health studies

Ying Liu, Donglin Zeng, Yuanjia Wang
2014 Shanghai Archives of Psychiatry  
The complexity, patient heterogeneity, and chronicity of mental disorders call for learning optimal DTRs to dynamically adapt treatment to an individual's response over time.  ...  This paper introduces DTRs and SMARTs using two examples in mental health studies, discusses two machine learning methods for estimating optimal DTR from SMARTs data, and demonstrates the performance of  ...  Table 2 . 2 Standardized coefficients for the optimal dynamic treatment rule estimated by various methods The reported coefficients were obtained from fitting a linear prediction rule for the outcome with  ... 
doi:10.11919/j.issn.1002-0829.214172 pmid:25642116 pmcid:PMC4311115 fatcat:rrpgzwwjlzd3bhe6ovdhzdsslu

Comment

Jingxiang Chen, Yufeng Liu, Donglin Zeng, Rui Song, Yingqi Zhao, Michael R. Kosorok
2016 Journal of the American Statistical Association  
We discuss two alternative methods, Q-learning and O-learning, to solve the same problem from the machine learning point of view.  ...  Xu, Müller, Wahed, and Thall proposed a Bayesian model to analyze an acute leukemia study involving multi-stage chemotherapy regimes.  ...  Q-Learning in Finding the Dynamic Treatment Regimes Q-learning is a reinforcement learning method that can be used to estimate the optimal personalized treatment strategy in a sequence of clinical decisions  ... 
doi:10.1080/01621459.2016.1200914 pmid:28003710 pmcid:PMC5167482 fatcat:xsnqgk57qjbendefjg27dgbkey

Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions

B. Zhang, A. A. Tsiatis, E. B. Laber, M. Davidian
2013 Biometrika  
Q-and A-learning are two main approaches for estimating the optimal regime, i.e., that yielding the most beneficial outcome in the patient population, using data from a clinical trial or observational  ...  A dynamic treatment regime is a list of sequential decision rules for assigning treatment based on a patient's history.  ...  Q-and A-learning are two main approaches for estimating the optimal dynamic treatment regime using data from a clinical trial or observational study.  ... 
doi:10.1093/biomet/ast014 pmid:24302771 pmcid:PMC3843953 fatcat:waa54cpndncj5jegplyvs7th7q

Optimization of multi-stage dynamic treatment regimes utilizing accumulated data

Xuelin Huang, Sangbum Choi, Lu Wang, Peter F. Thall
2015 Statistics in Medicine  
Simulation studies show that the modified Q-learning method has a higher probability of identifying the optimal treatment regime even in settings with misspecified models for outcomes.  ...  Recent applications include estimation of survival for dynamic treatment regimes in a sequentially randomized prostate cancer trial [17] and in a partially randomized trial of chemotherapy for acute leukemia  ...  Acknowledgements The authors acknowledge the support from the USA National Institutes of Health grants U54 CA096300, U01 CA152958, 5P50 CA100632, R01 CA 83932, and 5P01 CA055164.  ... 
doi:10.1002/sim.6558 pmid:26095711 pmcid:PMC4596799 fatcat:7abxelim2jhwfdrkyku7ypvhky

Dynamic Treatment Regimes

Bibhas Chakraborty, Susan A. Murphy
2014 Annual Review of Statistics and Its Application  
Statistics plays a key role in the construction of evidence-based dynamic treatment regimes - informing best study design as well as efficient estimation and valid inference.  ...  A dynamic treatment regime consists of a sequence of decision rules, one per stage of intervention, that dictate how to individualize treatments to patients based on evolving treatment and covariate history  ...  Acknowledgements We acknowledge support for this work from NIH grants RO1 MH080015 and P50 DA10075.  ... 
doi:10.1146/annurev-statistics-022513-115553 pmid:25401119 pmcid:PMC4231831 fatcat:gv7c4xlilbhfrla5tysdzyc7uu

Q-learning residual analysis: application to the effectiveness of sequences of antipsychotic medications for patients with schizophrenia

Ashkan Ertefaie, Susan Shortreed, Bibhas Chakraborty
2016 Statistics in Medicine  
An optimal dynamic treatment regime is composed of a sequence of decision rules that indicate how to optimally individualize treatment using the patients' baseline and time-varying characteristics to optimize  ...  Q-learning is a regression-based approach that uses longitudinal data to construct dynamic treatment regimes, which are sequences of decision rules that use patient information to inform future treatment  ...  Ertefaie is supported by award number P50 DA010075 and SES-1260782, from the National Institute on Drug Abuse and National Science Foundation. Dr.  ... 
doi:10.1002/sim.6859 pmid:26750518 pmcid:PMC4853263 fatcat:txq7mehdf5d2rpfccrdzen4m24

Dynamic Treatment Regimes [chapter]

Min Qian, Inbal Nahum-Shani, Susan A. Murphy
2012 Modern Clinical Trial Analysis  
We compare the SMART approach with other experimental approaches and discuss data analyses methods for constructing a high quality dynamic treatment regime as well as other secondary analyses.  ...  A dynamic treatment regime is a sequence of decision rules that specify how the dosage and/or type of treatment should be adjusted through time in response to an individual's changing needs, aiming to  ...  Acknowledgements We acknowledge support for this work from NIH grants RO1 MH080015 and P50 DA10075.  ... 
doi:10.1007/978-1-4614-4322-3_5 fatcat:max34trcnjgmlocw36rmfbheru

Deep advantage learning for optimal dynamic treatment regime

Shuhan Liang, Wenbin Lu, Rui Song
2018 Statistical Theory and Related Fields  
However few research has been done on deep advantage learning (A-learning). In this paper, we present a deep A-learning approach to estimate optimal dynamic treatment regime.  ...  The proposed deep A-learning methods are applied to a data from the STAR*D trial and are shown to have better performance compared with the penalized least square estimator using a linear decision rule  ...  In this paper, we propose a new method to estimate optimal dynamic treatment regime using deep A-learning.  ... 
doi:10.1080/24754269.2018.1466096 pmid:30420972 pmcid:PMC6226036 fatcat:mmfasu47qbefhacee7o7sbqfau

Penalized Q-Learning for Dynamic Treatment Regimes [article]

Rui Song, Weiwei Wang, Donglin Zeng, Michael R. Kosorok
2011 arXiv   pre-print
As these become more and more popular in conjunction with longitudinal data from clinical studies, the development of statistical inference for optimal dynamic treatment regimes is a high priority.  ...  A dynamic treatment regime effectively incorporates both accrued information and long-term effects of treatment from specially designed clinical trials.  ...  Extensive statistical estimating methods have also been proposed for optimal dynamic treatment regimes, including, for example, Chakraborty et al. (2009) , who developed a Q-learning framework based on  ... 
arXiv:1108.5338v1 fatcat:q4m4vksuwzd4rlu2drxlqqjloa

Q-Learning: Theory and Applications

Jesse Clifton, Eric Laber
2020 Annual Review of Statistics and Its Application  
In the context of personalized medicine, finite-horizon Q-learning is the workhorse for estimating optimal treatment strategies, known as treatment regimes.  ...  Q-learning, originally an incremental algorithm for estimating an optimal decision strategy in an infinite-horizon decision problem, now refers to a general class of reinforcement learning methods widely  ...  treatment regimes via Q-learning, and some remarks on prospects for combining Q-learning with model-based reinforcement learning methods.  ... 
doi:10.1146/annurev-statistics-031219-041220 fatcat:yh4itcu6ezecnig3ybpg4tpk4m
« Previous Showing results 1 — 15 out of 21,254 results