Filters








2,238 Hits in 6.7 sec

Incorporating causal factors into reinforcement learning for dynamic treatment regimes in HIV

Chao Yu, Yinzhao Dong, Jiming Liu, Guoqi Ren
2019 BMC Medical Informatics and Decision Making  
Reinforcement learning (RL) provides a promising technique to solve complex sequential decision making problems in health care domains.  ...  However, existing studies simply apply naive RL algorithms in discovering optimal treatment strategies for a targeted problem.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1186/s12911-019-0755-6 pmid:30961606 pmcid:PMC6454675 fatcat:ehbu3l5v3zf2ncpvtjtblvtjv4

Reinforcement Learning in Healthcare: A Survey [article]

Chao Yu, Jiming Liu, Shamim Nemati
2020 arXiv   pre-print
ranging from dynamic treatment regimes in chronic diseases and critical care, automated medical diagnosis from both unstructured and structured clinical data, as well as many other control or scheduling  ...  Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisions or treatment regimes are usually characterized  ...  How to model the time-varying causal relationships in healthcare and incorporate them into the learning process is therefore a challenging issue that requires more investigations.  ... 
arXiv:1908.08796v4 fatcat:iqqe3jifqvfntmxr6cakl4p2fy

Multi-stage optimal dynamic treatment regimes for survival outcomes with dependent censoring [article]

Hunyong Cho, Shannon T. Holloway, David J. Couper, Michael R. Kosorok
2022 arXiv   pre-print
We propose a reinforcement learning method for estimating an optimal dynamic treatment regime for survival outcomes with dependent censoring.  ...  The estimator allows the failure time to be conditionally independent of censoring and dependent on the treatment decision times, supports a flexible number of treatment arms and treatment stages, and  ...  The authors thank Donglin Zeng for bringing the composite criterion optimization into the discussion and the editors and anonymous reviewers for their constructive  ... 
arXiv:2012.03294v2 fatcat:oaer4wk5rbhqzooqrk5f3a5amm

Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions [article]

Nina Deliu, Joseph Jay Williams, Bibhas Chakraborty
2022 arXiv   pre-print
We provide the first unified instructive survey on RL methods for building AIs, encompassing both dynamic treatment regimes (DTRs) and just-in-time adaptive interventions in mobile health (mHealth).  ...  Reinforcement learning (RL) is acquiring a key role in the space of adaptive interventions (AIs), attracting a substantial interest within methodological and theoretical literature and becoming increasingly  ...  ACKNOWLEDGEMENTS Authors would like to thank Eric Laber for the constructive feedback received.  ... 
arXiv:2203.02605v1 fatcat:a5m6fa7ec5bznoghkgi3ojo3de

Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records [article]

Hua Zheng, Ilya O. Ryzhov, Wei Xie, Judy Zhong
2020 arXiv   pre-print
We developed an Artificial Intelligence algorithm, based on Reinforcement Learning (RL), for personalized diabetes and multi-morbidity management with strong potential to improve health outcomes relative  ...  The results demonstrate that the proposed personalized reinforcement learning prescriptive framework for type 2 diabetes yielded high concordance with clinicians' prescriptions and substantial improvements  ...  Reinforcement learning has been successfully applied in the past to single disease problems, such as blood glucose control (11) , HIV therapy (12) , cancer treatment (13) , anemia treatment in hemodialysis  ... 
arXiv:2011.02287v1 fatcat:zh55n34jyjcz5bfi7lgalowday

System dynamics applications to European health care issues

B C Dangerfield
1999 Journal of the Operational Research Society  
2 (TREATMENT) HIV STAGE 2 STAGE 1 HIV HIV - Low Infectiousness STAGE 3 HIV (CD4 <=200) inane Figure 8 Schematic flow diagram showing staging of the incubation distribution and the incorporation of pre-AIDS  ...  Keywords: system dynamics; health care; managerial learning; public policy; HIV/AIDS Introduction As a component of the public sector, health care looms large.  ... 
doi:10.1057/palgrave.jors.2600729 fatcat:loybcsqtbndrpctntgptss7ldu

Mobile Knowledge: HIV Patients' Encounter with Endocrinology

Cindy Patton
2007 Canadian Journal of Communication  
movement of information—and its limitations—in a unique setting: a metabolic disorders clinic for HIV-positive patients.  ...  This adaptation also occurs in the reverse, as patients adjust their thinking to make room for new information that will directly impact their treatment decisions.  ...  by the patients' own prior incorporation into another medical discipline's understanding of causal relations, treatment strategies, and the role of the doctor.  ... 
doi:10.22230/cjc.2007v32n3a1878 fatcat:2xxgqz6crrchhp5lw5t6jyxbga

Approaches for Framing Sustainability Challenges: Experiences from Swedish Sustainability Science Education [chapter]

Barry Ness
2019 Science for Sustainable Societies  
This chapter presents four different approaches that exist for framing sustainability challenge areas that are introduced and worked with by students in LUMES International Master Programme in Environmental  ...  be taught in sustainability science education.  ...  Causal Loop Diagrams A causal loop diagram (CLD) is a general approach to the qualitative analysis of systems; CLDs incorporate both human and social parameters into a single, sometimes sophisticated,  ... 
doi:10.1007/978-981-13-9061-6_3 fatcat:3lmy73o365aj3gpgnewcalkdsi

Personalized Dynamic Treatment Regimes in Continuous Time: A Bayesian Approach for Optimizing Clinical Decisions with Timing [article]

William Hua, Hongyuan Mei, Sarah Zohar, Magali Giral, Yanxun Xu
2021 arXiv   pre-print
Accurate models of clinical actions and their impacts on disease progression are critical for estimating personalized optimal dynamic treatment regimes (DTRs) in medical/health research, especially in  ...  while accounting for uncertainties in clinical observations learned from the posterior inference of the Bayesian joint model in the first step.  ...  Clifton and Laber (2020) reviewed the use of Q-learning, a general class of reinforcement learning methods, in estimating optimal treatment regimens taking the timing of treatments as given.  ... 
arXiv:2007.04155v3 fatcat:ps5nld2gw5cwpamayy25ele55e

Political repression, civil society and the politics of responding to AIDS in the BRICS nations

Eduardo J Gómez, Joseph Harris
2015 Health Policy and Planning  
costly for open democratic societies • Repressive nations with narrow civil society engagement can achieve relative success, even when responses are delayed, although further research into the mechanisms  ...  correlated with an aggressive response or better outcomes • In some cases, factors such as denialism, antagonistic state-civil society relations, and legacies of top-down governance can prove extremely  ...  Over the years, NAP officials have periodically visited local health participatory councils and AIDS NGOs to learn and incorporate their views into the policy-making process (Rich and Gó mez 2012) .  ... 
doi:10.1093/heapol/czv021 pmid:25858965 fatcat:5tmfbedlmvaztcq5d4apdlt6em

Trajectory Inspection: A Method for Iterative Clinician-Driven Design of Reinforcement Learning Studies

Christina X Ji, Michael Oberst, Sanjat Kanjilal, David Sontag
2021 AMIA Annual Symposium Proceedings  
However, treatment policies learned via RL from observational data are sensitive to subtle choices in study design.  ...  Reinforcement learning (RL) has the potential to significantly improve clinical decision making.  ...  Reinforcement learning (RL) has emerged as a popular tool for trying to learn effective policies for managing sequential decisions in patient treatments, including applications in sepsis treatment [1]  ... 
pmid:34457145 pmcid:PMC8378637 fatcat:7rt45oa34negxg7t4p4njmk7xy

Presidential Policy Initiatives: How the Public Learns about State of the Union Proposals from the Mass Media

JASON BARABAS
2008 Presidential Studies Quarterly  
, and the interaction of these two factors.  ...  In this powerful but underused design, individuals serve as counterfactuals for themselves, holding constant all relevant observed and unobserved characteristics.  ...  All factors considered, learning might be harder now.  ... 
doi:10.1111/j.1741-5705.2008.02636.x fatcat:65ef2dgsx5g3tco5gfpgxxenty

Is the Policy Win All? A Framework for Effective Social-Justice Advocacy

Barbara Klugman
2011 The Foundation Review  
I nevertheless want to thank the Ford Foundation for giving me two months' study leave, during which I investigated these issues.  ...  Acknowledgments The opinions expressed in this paper are those of the author and do not necessarily reflect those of the Ford Foundation.  ...  The emergence and growth of many HIV/AIDS organizations was indeed appropriate for this time, and critical in addressing the right to treatment for people living with HIV/AIDS.  ... 
doi:10.4087/foundationreview-d-10-00017 fatcat:qesfgsc2d5bs5evzfulov652xq

Bad Reputations: Memory, Corporeality, and the Limitations of Hacking's Looping Effects

Suze Berkhout
2014 PhaenEx: Journal of Existential and Phenomenological Theory and Culture  
Employing a field study of HIV/AIDS care in Vancouver, Canada, I push at some of the boundaries of Hacking's account, attempting to add complexity and nuance by bringing to bear considerations of memory  ...  In this paper, I examine limitations to Hacking's looping effects thesis, in an effort to further explore how kind-making may be embodied through intersections of subjectivity, social identity, and the  ...  13 I am grateful to the women who participated in the project, for their time and efforts. Thanks also to Scott Anderson and Sally Haslanger for their helpful comments on earlier drafts.  ... 
doi:10.22329/p.v9i2.4273 fatcat:apj3qqbwqvdyngsxn2pjavrqba

Personalized Dynamic Treatment Regimes in Continuous Time: A Bayesian Approach for Optimizing Clinical Decisions with Timing

William Hua, Hongyuan Mei, Sarah Zohar, Magali Giral, Yanxun Xu
2021 Bayesian Analysis  
Accurate models of clinical actions and their impacts on disease progression are critical for estimating personalized optimal dynamic treatment regimes (DTRs) in medical/health research, especially in  ...  while accounting for uncertainties in clinical observations learned from the posterior inference of the Bayesian joint model in the first step.  ...  Such scenarios are called dynamic treatment regimes (DTRs).  ... 
doi:10.1214/21-ba1276 fatcat:fdc6xkjwvfastopuncte4kqeha
« Previous Showing results 1 — 15 out of 2,238 results