Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies

• URL: http://arxiv.org/abs/2511.12075v1
• Date: Sat, 15 Nov 2025 07:37:49 GMT
• Title: Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies
• Abstract summary: We propose Treatment Stitching, a novel data augmentation framework that generates clinically valid treatment trajectories.<n>TreatStitch identifies similar intermediate patient states across different trajectories and stitches their respective segments.<n>By augmenting these synthetic trajectories into the original dataset, offline RL can learn from a more diverse dataset.
• Score: 16.34689464480395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive treatment strategies (ATS) are sequential decision-making processes that enable personalized care by dynamically adjusting treatment decisions in response to evolving patient symptoms. While reinforcement learning (RL) offers a promising approach for optimizing ATS, its conventional online trial-and-error learning mechanism is not permissible in clinical settings due to risks of harm to patients. Offline RL tackles this limitation by learning policies exclusively from historical treatment data, but its performance is often constrained by data scarcity-a pervasive challenge in clinical domains. To overcome this, we propose Treatment Stitching (TreatStitch), a novel data augmentation framework that generates clinically valid treatment trajectories by intelligently stitching segments from existing treatment data. Specifically, TreatStitch identifies similar intermediate patient states across different trajectories and stitches their respective segments. Even when intermediate states are too dissimilar to stitch directly, TreatStitch leverages the Schrödinger bridge method to generate smooth and energy-efficient bridging trajectories that connect dissimilar states. By augmenting these synthetic trajectories into the original dataset, offline RL can learn from a more diverse dataset, thereby improving its ability to optimize ATS. Extensive experiments across multiple treatment datasets demonstrate the effectiveness of TreatStitch in enhancing offline RL performance. Furthermore, we provide a theoretical justification showing that TreatStitch maintains clinical validity by avoiding out-of-distribution transitions.

Related papers

• Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes [1.2074766935042585]
  Clinicians may need to simultaneously optimize clinically relevant tails of the outcome distribution, control treatment-related risk, and choose among multiple treatment options.<n>Existing quantile dynamic treatment regime (DTR) methods capture distributional features of treatment outcomes but remain largely restricted to efficacy-only objectives and binary treatments.<n>We propose Risk-Aware Quantile Dynamic Treatment Regimes (RQDTR), a unified framework that optimize a prespecified quantile of the cumulative potential outcome while explicitly incorporating treatment-related risk.
  arXiv  Detail & Related papers  (2026-08-05T22:04:47Z)
• Optimizing Digital Therapeutic Interventions: Online Learning under Endogenous Adherence [0.6299766708197881]
  Digital therapeutics (DTs) provide a cost-effective way to manage interventions at scale through repeated interactions.<n> Behavioral psychology suggests that both treatment recommendations and past adherence affect future adherence.<n>We present a DT decision support framework that captures both recommendation and adherence effects.
  arXiv  Detail & Related papers  (2026-05-22T22:27:19Z)
• Doubly Robust Fusion of Many Treatments for Policy Learning [7.943530359935207]
  We propose a calibration-weighted treatment fusion procedure that robustly balances covariates across treatment groups.<n>We establish theoretical guarantees, including consistency, the oracle property of treatment fusion, and regret bounds.<n>We illustrate the practical utility of our method using a nationwide electronic health record-derived de-identified database.
  arXiv  Detail & Related papers  (2025-05-12T21:55:57Z)
• Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective [61.284843894545475]
  Complex algorithms for treatment effect estimation are ineffective when handling insufficiently labeled training sets.<n>We propose FCCM, which transforms the optimization objective into the textitFactual and textitCounterfactual Coverage Maximization to ensure effective radius reduction during data acquisition.<n> benchmarking FCCM against other baselines demonstrates its superiority across both fully synthetic and semi-synthetic datasets.
  arXiv  Detail & Related papers  (2025-05-08T13:42:00Z)
• Censoring-Aware Tree-Based Reinforcement Learning for Estimating Dynamic Treatment Regimes with Censored Outcomes [4.877686100899469]
  Censoring-Aware Tree-Based Reinforcement Learning (CA-TRL) is a novel framework to address the complexities associated with censored data.<n>We demonstrate its effectiveness through extensive simulations and real-world applications using the SANAD epilepsy dataset.
  arXiv  Detail & Related papers  (2025-03-09T16:53:09Z)
• Training and Validating a Treatment Recommender with Partial Verification Evidence [1.0693162404690828]
  Current clinical decision support systems (DSS) are trained and validated on observational data from the target clinic. This is problematic for treatments validated in a randomized clinical trial (RCT) but not yet introduced in any clinic. Key challenges we address are of missingness -- missing rationale for treatment assignment (the assignment is at random), and missing verification evidence.
  arXiv  Detail & Related papers  (2024-06-10T09:23:00Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation [73.83178465971552]
  The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. We propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective.
  arXiv  Detail & Related papers  (2023-07-27T08:58:05Z)
• Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications [3.770564448216192]
  We introduce a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training. We perform extensive experiments on two real-world tasks for diabetes and sepsis treatment optimization. Across a range of principled and clinically relevant metrics, we show that our proposed approach enables substantial improvements in expected health outcomes.
  arXiv  Detail & Related papers  (2023-02-15T09:30:57Z)
• Federated Offline Reinforcement Learning [55.326673977320574]
  We propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. We design the first federated policy optimization algorithm for offline RL with sample complexity. We give a theoretical guarantee for the proposed algorithm, where the suboptimality for the learned policies is comparable to the rate as if data is not distributed.
  arXiv  Detail & Related papers  (2022-06-11T18:03:26Z)
• Assessment of Treatment Effect Estimators for Heavy-Tailed Data [70.72363097550483]
  A central obstacle in the objective assessment of treatment effect (TE) estimators in randomized control trials (RCTs) is the lack of ground truth (or validation set) to test their performance. We provide a novel cross-validation-like methodology to address this challenge. We evaluate our methodology across 709 RCTs implemented in the Amazon supply chain.
  arXiv  Detail & Related papers  (2021-12-14T17:53:01Z)
• DTR Bandit: Learning to Make Response-Adaptive Decisions With Low Regret [59.81290762273153]
  Dynamic treatment regimes (DTRs) are personalized, adaptive, multi-stage treatment plans that adapt treatment decisions to an individual's initial features and to intermediate outcomes and features at each subsequent stage. We propose a novel algorithm that, by carefully balancing exploration and exploitation, is guaranteed to achieve rate-optimal regret when the transition and reward models are linear.
  arXiv  Detail & Related papers  (2020-05-06T13:03:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.