Methodological Challenges in Constructing Effective Treatment Sequences for Chronic Psychiatric Disorders

By Susan A. Murphy, David W Oslin, A. Rush, Ji Zhu. 2007

116 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Experimental and Cognitive Psychology, Pharmacology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Experimental and Cognitive Psychology

In Pharmacology

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, neutral): “time [152].”
Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data (2017, methodology): “The objective is to maximize V ( π) and the so-called Q-function is the expected reward if a subject is assigned to the optimal treatment in all the future stages, and can be estimated through Dynamic Programming following the ideas from Q-learning [15].”
Learning Optimal Individualized Treatment Rules from Electronic Health Record Data (2016, methodology): “Statistical methods for estimating optimal medical treatment and disease management strategy according to patient-speciﬁc characteristics for each individual have received extensive attention in the recent literature [3], [4], [5], [6].”
Adaptive treatment of anemia on hemodialysis patients: A reinforcement learning approach (2011, methodology): “the design of ATS has been recently applied to the treatment of chronic psychiatric disorders [10], epilepsy [11] or lung cancer”
Reinforcement learning design for cancer clinical trials (2009, unknown): “[9] suggest Q-learning, which is one of the most important breakthroughs in reinforcement learning, for constructing decision rules for chronic psychiatric disorders, since these chronic conditions often require sequential decision making to achieve the best clinical outcomes.”
Augmented outcome-weighted learning for estimating optimal dynamic treatment regimens (2018, methodology): “For example, Q-learning 16 was used to analyze SMART data by Zhao et al 9 and Murphy et al. 17 In this learning algorithm, the optimal treatment at each stage is derived from a backward induction by maximizing the so-called Q-function (“Q” stands for “quality of action”), which is estimated via a…”
New Statistical Learning Methods for Estimating Optimal Dynamic Treatment Regimes (2015, methodology): “The foregoing assumptions are satisfied when data are collected in a SMART (Lavori and Dawson 2004).”
Adaptive Control of Epileptic Seizures using Reinforcement Learning (2010, background): “This situation is rapidly changing: the medical community has a strong interest in designing studies with multiple sequential, randomized trials [48].”
Adaptive Interventions Treatment Modelling and Regimen Optimization Using Sequential Multiple Assignment Randomized Trials (Smart) and Q-Learning (2018, methodology): “Similarly, Q-learning was implemented for defining decision rules in chronic psychiatric disorders [9] and also been successfully applied for segmenting prostrate in transrectal ultrasound images [59].”
Optimization of anemia treatment in hemodialysis patients via reinforcement learning (2014, background): “Recently there has been a growing interest in appl ying FQI to optimize the treatment of several diseases includ ing HIV /AIDS [34], psychiatric disorders [35], epilepsy [36, 37], schizophrenia [38, 39] or smoking addiction [40].”
Q-LEARNING WITH CENSORED DATA (2012, methodology): “The approach closest to our proposal is the censored-Q-learning algo-rithm of Zhao et al. (2011).”
Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis (2010, methodology): “Reinforcement learning methods (Pineau et al., 2007) have been used in evidence-based medicine to analyze multi-stage randomized controlled trials (Murphy et al., 2007; Zhao et al., 2009).”
Constructing Dynamic Treatment Regimes in Infinite-Horizon Settings (2014, unknown): “Q-learning, a reinforcement learning algorithm, is also widely used in constructing the optimal regime (Murphy et al., 2006; ZHAO et al., 2009; Chakraborty et al., 2010; NahumShani et al., 2012).”