mlsanityData to 7 Oct 2026

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data

arXiv 1801.09271 ↗First posted 28 Jan 2018cs.AI stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexity in heterogeneous disease progression and treatment choices, with the goal of providing doctor and patients the data-driven personalized decision recommendations. The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and (ii) a deep reinforcement learning step to estimate the long-term value function of Dynamic Treatment Regimes. Both steps depend on deep neural networks. As a key motivational example, we have implemented the proposed framework on a data set from the Center for International Bone Marrow Transplant Research (CIBMTR) registry database, focusing on the sequence of prevention and treatments for acute and chronic graft versus host disease after transplantation. In the experimental results, we have demonstrated promising accuracy in predicting human experts' decisions, as well as the high expected reward function in the DRL-based dynamic treatment regimes.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 4; 2024: 6; 2025: 6; 2026: 1.

23 papers.

Sort:

By area:

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  2. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 36
  3. 2023Corruption-Robust Offline Reinforcement Learning with General Function Approximationcited by 30
  4. 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitationcited by 15
  5. 2021Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settingscited by 14
  6. 2022Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventionscited by 6
  7. 2023Model Based Reinforcement Learning for Personalized Heparin Dosingcited by 5
  8. 2024Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexaminationcited by 5
  9. 2022Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicinecited by 4
  10. 2022There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazescited by 4
  11. 2024Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimescited by 3
  12. 2025Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPscited by 3
11 more
  1. 2025Online Decision Making with Generative Action Setscited by 2
  2. 2023A optimization framework for herbal prescription planning based on deep reinforcement learningcited by 1
  3. 2024Prompting Large Language Models for Supporting the Differential Diagnosis of Anemiacited by 1
  4. 2025How to Provably Improve Return Conditioned Supervised Learning?cited by 1
  5. 2025TECM*: A Data-Driven Assessment to Reinforcement Learning Methods and Application to Heparin Treatment Strategy for Surgical Sepsiscited by 1
  6. 2026The hidden risks of temporal resampling in clinical reinforcement learningcited by 1
  7. 2021An Analysis of Reinforcement Learning for Malaria Controlcited by 0
  8. 2023Context-Aware Composition of Agent Policies by Markov Decision Process Entity Embeddings and Agent Ensemblescited by 0
  9. 2024Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancementcited by 0
  10. 2024Artificial Intelligence-based Decision Support Systems for Precision and Digital Healthcited by 0
  11. 2025Where to Intervene: Action Selection in Deep Reinforcement Learningcited by 0