Dynamic Treatment Regimes

Toward Precision in Critical Care Research: Methods for Observational and Interventional Studies

Critical care trials evaluate the effect of interventions in patients with diverse personal histories and causes of illness, often under the umbrella of heterogeneous clinical syndromes, such as sepsis or acute respiratory distress syndrome. Given this variation, it is reasonable to expect that the effect of treatment on outcomes may differ for individuals with variable characteristics. However, in randomized controlled trials, efficacy is typically assessed by the average treatment effect (ATE), which quantifies the average effect of the intervention on the outcome in the study population. Importantly, the ATE may hide variations of the treatment's effect on a clinical outcome across levels of patient characteristics, which may erroneously lead to the conclusion that an intervention does not work overall when it may in fact benefit certain patients. In this review, we describe methodological approaches for assessing heterogeneity of treatment effect (HTE), including expert-derived subgrouping, data-driven subgrouping, baseline risk modeling, treatment effect modeling, and individual treatment rule estimation. Next, we outline how insights from HTE analyses can be incorporated into the design of clinical trials. Finally, we propose a research agenda for advancing the field and bringing HTE approaches to the bedside.

Model-Informed Reinforcement Learning for Enabling Precision Dosing Via Adaptive Dosing

Precision dosing, the tailoring of drug doses to optimize therapeutic benefits and minimize risks in each patient, is essential for drugs with a narrow therapeutic window and severe adverse effects. Adaptive dosing strategies extend the precision dosing concept to time-varying treatments which require sequential dose adjustments based on evolving patient conditions. Reinforcement learning (RL) naturally fits this paradigm: it perfectly mimics the sequential decision-making process where clinicians adapt dose administration based on patient response and evolution monitoring. This paper aims to investigate the potentiality of coupling RL with population PK/PD models to develop precision dosing algorithms, reviewing the most relevant works in the field. Case studies in which PK/PD models were integrated within RL algorithms as simulation engine to predict consequences of any dosing action have been considered and discussed. They mainly concern propofol-induced anesthesia, anticoagulant therapy with warfarin and a variety of anticancer treatments differing for administered agents and/or monitored biomarkers. The resulted picture highlights a certain heterogeneity in terms of precision dosing approaches, applied methodologies, and degree of adherence to the clinical domain. In addition, a tutorial on how a precision dosing problem should be formulated in terms of the key elements composing the RL framework (i.e., system state, agent actions and reward function), and on how PK/PD models could enhance RL approaches is proposed for readers interested in delving in this field. Overall, the integration of PK/PD models into a RL-framework holds great promise for precision dosing, but further investigations and advancements are still needed to address current limitations and extend the applicability of this methodology to drugs requiring adaptive dosing strategies.

Estimating optimal decision trees for treatment assignment: The case of K > 2 treatment alternatives

For many problems in clinical practice, multiple treatment alternatives are available. Given data from a randomized controlled trial or an observational study, an important challenge is to estimate an optimal decision rule that specifies for each client the most effective treatment alternative, given his or her pattern of pretreatment characteristics. In the present paper we will look for such a rule within the insightful family of classification trees. Unfortunately, however, there is dearth of readily accessible software tools for optimal decision tree estimation in the case of more than two treatment alternatives. Moreover, this primary tree estimation problem is also cursed with two secondary problems: a structural missingness in typical studies on treatment evaluation (because every individual is assigned to a single treatment alternative only), and a major issue of replicability. In this paper we propose solutions for both the primary and the secondary problems at stake. We evaluate the proposed solution in a simulation study, and illustrate with an application on the search for an optimal tree-based treatment regime in a randomized controlled trial on K = 3 different types of aftercare for younger women with early-stage breast cancer. We conclude by arguing that the proposed solutions may have relevance for several other classification problems inside and outside the domain of optimal treatment assignment.

Leveraging Artificial Intelligence to Optimize Transcranial Direct Current Stimulation for Long COVID Management: A Forward-Looking Perspective

Long COVID (Coronavirus disease), affecting millions globally, presents unprecedented challenges to healthcare systems due to its complex, multifaceted nature and the lack of effective treatments. This perspective review explores the potential of artificial intelligence (AI)-guided transcranial direct current stimulation (tDCS) as an innovative approach to address the urgent need for effective Long COVID management. The authors examine how AI could optimize tDCS protocols, enhance clinical trial design, and facilitate personalized treatment for the heterogeneous manifestations of Long COVID. Key areas discussed include AI-driven personalization of tDCS parameters based on individual patient characteristics and real-time symptom fluctuations, the use of machine learning for patient stratification, and the development of more sensitive outcome measures in clinical trials. This perspective addresses ethical considerations surrounding data privacy, algorithmic bias, and equitable access to AI-enhanced treatments. It also explores challenges and opportunities for implementing AI-guided tDCS across diverse healthcare settings globally. Future research directions are outlined, including the need for large-scale validation studies and investigations of long-term efficacy and safety. The authors argue that while AI-guided tDCS shows promise for addressing the complex nature of Long COVID, significant technical, ethical, and practical challenges remain. They emphasize the importance of interdisciplinary collaboration, patient-centered approaches, and a commitment to global health equity in realizing the potential of this technology. This perspective article provides a roadmap for researchers, clinicians, and policymakers involved in developing and implementing AI-guided neuromodulation therapies for Long COVID and potentially other neurological and psychiatric conditions.

Machine learning for antidepressant treatment selection in depression

Finding the right antidepressant for the individual patient with major depressive disorder can be a difficult endeavor and is mostly based on trial-and-error. Machine learning (ML) is a promising tool to personalize antidepressant prescription. In this review, we summarize the current evidence of ML in the selection of antidepressants and conclude that its value for clinical practice is still limited. Apart from the current focus on effectiveness, several other factors should be taken into account to make ML-based prediction models useful for clinical application.

Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data

In this paper, we review recent advances in statistical methods for the evaluation of the heterogeneity of treatment effects (HTE), including subgroup identification and estimation of individualized treatment regimens, from randomized clinical trials and observational studies. We identify several types of approaches using the features introduced in Lipkovich et al (Stat Med 2017;36: 136-196) that distinguish the recommended principled methods from basic methods for HTE evaluation that typically rely on rules of thumb and general guidelines (the methods are often referred to as common practices). We discuss the advantages and disadvantages of various principled methods as well as common measures for evaluating their performance. We use simulated data and a case study based on a historical clinical trial to illustrate several new approaches to HTE evaluation.

A generalized outcome-adaptive sequential multiple assignment randomized trial design

A dynamic treatment regime (DTR) is a mathematical representation of a multistage decision process. When applied to sequential treatment selection in medical settings, DTRs are useful for identifying optimal therapies for chronic diseases such as AIDs, mental illnesses, substance abuse, and many cancers. Sequential multiple assignment randomized trials (SMARTs) provide a useful framework for constructing DTRs and providing unbiased between-DTR comparisons. A limitation of SMARTs is that they ignore data from past patients that may be useful for reducing the probability of exposing new patients to inferior treatments. In practice, this may result in decreased treatment adherence or dropouts. To address this problem, we propose a generalized outcome-adaptive (GO) SMART design that adaptively unbalances stage-specific randomization probabilities in favor of treatments observed to be more effective in previous patients. To correct for bias induced by outcome adaptive randomization, we propose G-estimators and inverse-probability-weighted estimators of DTR effects embedded in a GO-SMART and show analytically that they are consistent. We report simulation results showing that, compared to a SMART, Response-Adaptive SMART and SMART with adaptive randomization, a GO-SMART design treats significantly more patients with the optimal DTR and achieves a larger number of total responses while maintaining similar or better statistical power.

Advancing randomized controlled trial methodologies: The place of innovative trial design in eating disorders research

Randomized controlled trials can be used to generate evidence on the efficacy and safety of new treatments in eating disorders research. Many of the trials previously conducted in this area have been deemed to be of low quality, in part due to a number of practical constraints. This article provides an overview of established and more innovative clinical trial designs, accompanied by pertinent examples, to highlight how design choices can enhance flexibility and improve efficiency of both resource allocation and participant involvement. Trial designs include individually randomized, cluster randomized, and designs with randomizations at multiple time points and/or addressing several research questions (master protocol studies). Design features include the use of adaptations and considerations for pragmatic or registry-based trials. The appropriate choice of trial design, together with rigorous trial conduct, reporting and analysis, can establish high-quality evidence to advance knowledge in the field. It is anticipated that this article will provide a broad and contemporary introduction to trial designs and will help researchers make informed trial design choices for improved testing of new interventions in eating disorders. PUBLIC SIGNIFICANCE: There is a paucity of high quality randomized controlled trials that have been conducted in eating disorders, highlighting the need to identify where efficiency gains in trial design may be possible to advance the eating disorder research field. We provide an overview of some key trial designs and features which may offer solutions to practical constraints and increase trial efficiency.

A matching-based machine learning approach to estimating optimal dynamic treatment regimes with time-to-event outcomes

Observational data (e.g. electronic health records) has become increasingly important in evidence-based research on dynamic treatment regimes, which tailor treatments over time to patients based on their characteristics and evolving clinical history. It is of great interest for clinicians and statisticians to identify an optimal dynamic treatment regime that can produce the best expected clinical outcome for each individual and thus maximize the treatment benefit over the population. Observational data impose various challenges for using statistical tools to estimate optimal dynamic treatment regimes. Notably, the task becomes more sophisticated when the clinical outcome of primary interest is time-to-event. Here, we propose a matching-based machine learning method to identify the optimal dynamic treatment regime with time-to-event outcomes subject to right-censoring using electronic health record data. In contrast to the established inverse probability weighting-based dynamic treatment regime methods, our proposed approach provides better protection against model misspecification and extreme weights in the context of treatment sequences, effectively addressing a prevalent challenge in the longitudinal analysis of electronic health record data. In simulations, the proposed method demonstrates robust performance across a range of scenarios. In addition, we illustrate the method with an application to estimate optimal dynamic treatment regimes for patients with advanced non-small cell lung cancer using a real-world, nationwide electronic health record database from Flatiron Health.

Intricacies of Human-AI Interaction in Dynamic Decision-Making for Precision Oncology: A Case Study in Response-Adaptive Radiotherapy

Background

Adaptive treatment strategies that can dynamically react to individual cancer progression can provide effective personalized care. Longitudinal multi-omics information, paired with an artificially intelligent clinical decision support system (AI-CDSS) can assist clinicians in determining optimal therapeutic options and treatment adaptations. However, AI-CDSS is not perfectly accurate, as such, clinicians' over/under reliance on AI may lead to unintended consequences, ultimately failing to develop optimal strategies. To investigate such collaborative decision-making process, we conducted a Human-AI interaction case study on response-adaptive radiotherapy (RT).

Methods

We designed and conducted a two-phase study for two disease sites and two treatment modalities-adaptive RT for non-small cell lung cancer (NSCLC) and adaptive stereotactic body RT for hepatocellular carcinoma (HCC)-in which clinicians were asked to consider mid-treatment modification of the dose per fraction for a number of retrospective cancer patients without AI-support (Unassisted Phase) and with AI-assistance (AI-assisted Phase). The AI-CDSS graphically presented trade-offs in tumor control and the likelihood of toxicity to organs at risk, provided an optimal recommendation, and associated model uncertainties. In addition, we asked for clinicians' decision confidence level and trust level in individual AI recommendations and encouraged them to provide written remarks. We enrolled 13 evaluators (radiation oncology physicians and residents) from two medical institutions located in two different states, out of which, 4 evaluators volunteered in both NSCLC and HCC studies, resulting in a total of 17 completed evaluations (9 NSCLC, and 8 HCC). To limit the evaluation time to under an hour, we selected 8 treated patients for NSCLC and 9 for HCC, resulting in a total of 144 sets of evaluations (72 from NSCLC and 72 from HCC). Evaluation for each patient consisted of 8 required inputs and 2 optional remarks, resulting in up to a total of 1440 data points.

Results

AI-assistance did not homogeneously influence all experts and clinical decisions. From NSCLC cohort, 41 (57%) decisions and from HCC cohort, 34 (47%) decisions were adjusted after AI assistance. Two evaluations (12%) from the NSCLC cohort had zero decision adjustments, while the remaining 15 (88%) evaluations resulted in at least two decision adjustments. Decision adjustment level positively correlated with dissimilarity in decision-making with AI [NSCLC: ρ = 0.53 ( p < 0.001); HCC: ρ = 0.60 ( p < 0.001)] indicating that evaluators adjusted their decision closer towards AI recommendation. Agreement with AI-recommendation positively correlated with AI Trust Level [NSCLC: ρ = 0.59 ( p < 0.001); HCC: ρ = 0.7 ( p < 0.001)] indicating that evaluators followed AI's recommendation if they agreed with that recommendation. The correlation between decision confidence changes and decision adjustment level showed an opposite trend [NSCLC: ρ = -0.24 ( p = 0.045), HCC: ρ = 0.28 ( p = 0.017)] reflecting the difference in behavior due to underlying differences in disease type and treatment modality. Decision confidence positively correlated with the closeness of decisions to the standard of care (NSCLC: 2 Gy/fx; HCC: 10 Gy/fx) indicating that evaluators were generally more confident in prescribing dose fractionations more similar to those used in standard clinical practice. Inter-evaluator agreement increased with AI-assistance indicating that AI-assistance can decrease inter-physician variability. The majority of decisions were adjusted to achieve higher tumor control in NSCLC and lower normal tissue complications in HCC. Analysis of evaluators' remarks indicated concerns for organs at risk and RT outcome estimates as important decision-making factors.

Conclusions

Human-AI interaction depends on the complex interrelationship between expert's prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. The collaborative decision-making process can be summarized as follows: (i) some clinicians may not believe in an AI system, completely disregarding its recommendation, (ii) some clinicians may believe in the AI system but will critically analyze its recommendations on a case-by-case basis; (iii) when a clinician finds that the AI recommendation indicates the possibility for better outcomes they will adjust their decisions accordingly; and (iv) When a clinician finds that the AI recommendation indicate a worse possible outcome they will disregard it and seek their own alternative approach.

Optimizing Contingency Management with Reinforcement Learning

Contingency Management (CM) is a psychological treatment that aims to change behavior with financial incentives. In substance use disorders (SUDs), deployment of CM has been enriched by longstanding discussions around the cost-effectiveness of prized-based and voucher-based approaches. In prize-based CM, participants earn draws to win prizes, including small incentives to reduce costs, and the number of draws escalates depending on the duration of maintenance of abstinence. In voucher-based CM, participants receive a predetermined voucher amount based on specific substance test results. While both types have enhanced treatment outcomes, there is room for improvement in their cost-effectiveness: the voucher-based system requires enduring financial investment; the prize-based system might sacrifice efficacy. Previous work in computational psychiatry of SUDs typically employs frameworks wherein participants make decisions to maximize their expected compensation. In contrast, we developed new frameworks that clinical decision-makers choose actions, CM structures, to reinforce the substance abstinence behavior of participants. We consider the choice of the voucher or prize to be a sequential decision, where there are two pivotal parameters: the prize probability for each draw and the escalation rule determining the number of draws. Recent advancements in Reinforcement Learning, more specifically, in off-policy evaluation, afforded techniques to estimate outcomes for different CM decision scenarios from observed clinical trial data. We searched CM schemas that maximized treatment outcomes with budget constraints. Using this framework, we analyzed data from the Clinical Trials Network to construct unbiased estimators on the effects of new CM schemas. Our results indicated that the optimal CM schema would be to strengthen reinforcement rapidly in the middle of the treatment course. Our estimated optimal CM policy improved treatment outcomes by 32% while maintaining costs. Our methods and results have broad applications in future clinical trial planning and translational investigations on the neurobiological basis of SUDs.

Integrating randomized and observational studies to estimate optimal dynamic treatment regimes

Sequential multiple assignment randomized trials (SMARTs) are the gold standard for estimating optimal dynamic treatment regimes (DTRs), but are costly and require a large sample size. We introduce the multi-stage augmented Q-learning estimator (MAQE) to improve efficiency of estimation of optimal DTRs by augmenting SMART data with observational data. Our motivating example comes from the Back Pain Consortium, where one of the overarching aims is to learn how to tailor treatments for chronic low back pain to individual patient phenotypes, knowledge which is lacking clinically. The Consortium-wide collaborative SMART and observational studies within the Consortium collect data on the same participant phenotypes, treatments, and outcomes at multiple time points, which can easily be integrated. Previously published single-stage augmentation methods for integration of trial and observational study (OS) data were adapted to estimate optimal DTRs from SMARTs using Q-learning. Simulation studies show the MAQE, which integrates phenotype, treatment, and outcome information from multiple studies over multiple time points, more accurately estimates the optimal DTR, and has a higher average value than a comparable Q-learning estimator without augmentation. We demonstrate this improvement is robust to a wide range of trial and OS sample sizes, addition of noise variables, and effect sizes.

Handling time-varying treatments in observational studies: A scoping review and recommendations

OBJECTIVE

Time-varying treatments are common in observational studies. However, when assessing treatment effects, the methodological framework has not been systematically established for handling time-varying treatments. This study aimed to examine the current methods for dealing with time-varying treatments in observational studies and developed practical recommendations.

METHODS

We searched PubMed from 2000 to 2021 for methodological articles about time-varying treatments, and qualitatively summarized the current methods for handling time-varying treatments. Subsequently, we developed practical recommendations through interactive internal group discussions and consensus by a panel of external experts.

RESULTS

Of the 36 eligible reports (22 methodological reviews, 10 original studies, 2 tutorials and 2 commentaries), most examined statistical methods for time-varying treatments, and only a few discussed the overarching methodological process. Generally, there were three methodological components to handle time-varying treatments. These included the specification of treatment which may be categorized as three scenarios (i.e., time-independent treatment, static treatment regime, or dynamic treatment regime); definition of treatment status which could involve three approaches (i.e., intention-to-treat, per-protocol, or as-treated approach); and selection of analytic methods. Based on the review results, a methodological workflow and a set of practical recommendations were proposed through two consensus meetings.

CONCLUSIONS

There is no consensus process for assessing treatment effects in observational studies with time-varying treatments. Previous efforts were dedicated to developing statistical methods. Our study proposed a stepwise workflow with practical recommendations to assist the practice.

Optimizing warfarin dosing for patients with atrial fibrillation using machine learning

While novel oral anticoagulants are increasingly used to reduce risk of stroke in patients with atrial fibrillation, vitamin K antagonists such as warfarin continue to be used extensively for stroke prevention across the world. While effective in reducing the risk of strokes, the complex pharmacodynamics of warfarin make it difficult to use clinically, with many patients experiencing under- and/or over- anticoagulation. In this study we employed a novel implementation of deep reinforcement learning to provide clinical decision support to optimize time in therapeutic International Normalized Ratio (INR) range. We used a novel semi-Markov decision process formulation of the Batch-Constrained deep Q-learning algorithm to develop a reinforcement learning model to dynamically recommend optimal warfarin dosing to achieve INR of 2.0-3.0 for patients with atrial fibrillation. The model was developed using data from 22,502 patients in the warfarin treated groups of the pivotal randomized clinical trials of edoxaban (ENGAGE AF-TIMI 48), apixaban (ARISTOTLE) and rivaroxaban (ROCKET AF). The model was externally validated on data from 5730 warfarin-treated patients in a fourth trial of dabigatran (RE-LY) using multilevel regression models to estimate the relationship between center-level algorithm consistent dosing, time in therapeutic INR range (TTR), and a composite clinical outcome of stroke, systemic embolism or major hemorrhage. External validation showed a positive association between center-level algorithm-consistent dosing and TTR (R2 = 0.56). Each 10% increase in algorithm-consistent dosing at the center level independently predicted a 6.78% improvement in TTR (95% CI 6.29, 7.28; p < 0.001) and a 11% decrease in the composite clinical outcome (HR 0.89; 95% CI 0.81, 1.00; p = 0.015). These results were comparable to those of a rules-based clinical algorithm used for benchmarking, for which each 10% increase in algorithm-consistent dosing independently predicted a 6.10% increase in TTR (95% CI 5.67, 6.54, p < 0.001) and a 10% decrease in the composite outcome (HR 0.90; 95% CI 0.83, 0.98, p = 0.018). Our findings suggest that a deep reinforcement learning algorithm can optimize time in therapeutic range for patients taking warfarin. A digital clinical decision support system to promote algorithm-consistent warfarin dosing could optimize time in therapeutic range and improve clinical outcomes in atrial fibrillation globally.

Machine Learning and Health Science Research: Tutorial

Machine learning (ML) has seen impressive growth in health science research due to its capacity for handling complex data to perform a range of tasks, including unsupervised learning, supervised learning, and reinforcement learning. To aid health science researchers in understanding the strengths and limitations of ML and to facilitate its integration into their studies, we present here a guideline for integrating ML into an analysis through a structured framework, covering steps from framing a research question to study design and analysis techniques for specialized data types.

Multiobjective tree-based reinforcement learning for estimating tolerant dynamic treatment regimes

A dynamic treatment regime (DTR) is a sequence of treatment decision rules that dictate individualized treatments based on evolving treatment and covariate history. It provides a vehicle for optimizing a clinical decision support system and fits well into the broader paradigm of personalized medicine. However, many real-world problems involve multiple competing priorities, and decision rules differ when trade-offs are present. Correspondingly, there may be more than one feasible decision that leads to empirically sufficient optimization. In this paper, we propose a concept of "tolerant regime," which provides a set of individualized feasible decision rules under a prespecified tolerance rate. A multiobjective tree-based reinforcement learning (MOT-RL) method is developed to directly estimate the tolerant DTR (tDTR) that optimizes multiple objectives in a multistage multitreatment setting. At each stage, MOT-RL constructs an unsupervised decision tree by modeling the counterfactual mean outcome of each objective via semiparametric regression and maximizing a purity measure constructed by the scalarized augmented inverse probability weighted estimators (SAIPWE). The algorithm is implemented in a backward inductive manner through multiple decision stages, and it estimates the optimal DTR and tDTR depending on the decision-maker's preferences. Multiobjective tree-based reinforcement learning is robust, efficient, easy-to-interpret, and flexible to different settings. We apply MOT-RL to evaluate 2-stage chemotherapy regimes that reduce disease burden and prolong survival for advanced prostate cancer patients using a dataset collected at MD Anderson Cancer Center.

Reflections on the concept of optimality of single decision point treatment regimes

In many areas, applied researchers as well as practitioners have to choose between different solutions for a problem at hand; this calls for optimal decision rules to settle the choices involved. As a key example, one may think of the search for optimal treatment regimes (OTRs) in clinical research, that specify which treatment alternative should be administered to each patient under study. Motivated by the fact that the concept of optimality of decision rules in general and treatment regimes in particular has received so far relatively little attention and discussion, we will present a number of reflections on it, starting from the basics of any optimization problem. Specifically, we will analyze the search space and the to be optimized criterion function underlying the search of single decision point OTRs, along with the many choice aspects that show up in their specification. Special attention is paid to formal characteristics and properties as well as to substantive concerns and hypotheses that may guide these choices. We illustrate with a few empirical examples taken from the literature. Finally, we discuss how the presented reflections may help sharpen statistical thinking about optimality of decision rules for treatment assignment and to facilitate the dialogue between the statistical consultant and the applied researcher in search of an OTR.

Modified interactive Q-learning for attenuating the impact of model misspecification with treatment effect heterogeneity

A sequential multiple assignment randomized trial, which incorporates multiple stages of randomization, is a popular approach for collecting data to inform personalized and adaptive treatments. There is an extensive literature on statistical methods to analyze data collected in sequential multiple assignment randomized trials and estimate the optimal dynamic treatment regime. Q-learning with linear regression is widely used for this purpose due to its ease of implementation. However, model misspecification is a common problem with this approach, and little attention has been given to the impact of model misspecification when treatment effects are heterogeneous across subjects. This article describes the integrative impact of two possible types of model misspecification related to treatment effect heterogeneity: omitted early-stage treatment effects in late-stage main effect model, and violated linearity assumption between pseudo-outcomes and predictors despite non-linearity arising from the optimization operation. The proposed method, aiming to deal with both types of misspecification concomitantly, builds interactive models into modified parametric Q-learning with Murphy's regret function. Simulations show that the proposed method is robust to both sources of model misspecification. The proposed method is applied to a two-stage sequential multiple assignment randomized trial with embedded tailoring aimed at reducing binge drinking in first-year college students.

Machine learning applications and challenges in graft-versus-host disease: a scoping review

PURPOSE OF REVIEW

This review delves into the potential of artificial intelligence (AI), particularly machine learning (ML), in enhancing graft-versus-host disease (GVHD) risk assessment, diagnosis, and personalized treatment.

RECENT FINDINGS

Recent studies have demonstrated the superiority of ML algorithms over traditional multivariate statistical models in donor selection for allogeneic hematopoietic stem cell transplantation. ML has recently enabled dynamic risk assessment by modeling time-series data, an upgrade from the static, "snapshot" assessment of patients that conventional statistical models and older ML algorithms offer. Regarding diagnosis, a deep learning model, a subset of ML, can accurately identify skin segments affected with chronic GVHD with satisfactory results. ML methods such as Q-learning and deep reinforcement learning have been utilized to develop adaptive treatment strategies (ATS) for the personalized prevention and treatment of acute and chronic GVHD.

SUMMARY

To capitalize on these promising advancements, there is a need for large-scale, multicenter collaborations to develop generalizable ML models. Furthermore, addressing pertinent issues such as the implementation of stringent ethical guidelines is crucial before the widespread introduction of AI into GVHD care.

Interpreting Randomized Controlled Trials

This article describes rationales and limitations for making inferences based on data from randomized controlled trials (RCTs). We argue that obtaining a representative random sample from a patient population is impossible for a clinical trial because patients are accrued sequentially over time and thus comprise a convenience sample, subject only to protocol entry criteria. Consequently, the trial's sample is unlikely to represent a definable patient population. We use causal diagrams to illustrate the difference between random allocation of interventions within a clinical trial sample and true simple or stratified random sampling, as executed in surveys. We argue that group-specific statistics, such as a median survival time estimate for a treatment arm in an RCT, have limited meaning as estimates of larger patient population parameters. In contrast, random allocation between interventions facilitates comparative causal inferences about between-treatment effects, such as hazard ratios or differences between probabilities of response. Comparative inferences also require the assumption of transportability from a clinical trial's convenience sample to a targeted patient population. We focus on the consequences and limitations of randomization procedures in order to clarify the distinctions between pairs of complementary concepts of fundamental importance to data science and RCT interpretation. These include internal and external validity, generalizability and transportability, uncertainty and variability, representativeness and inclusiveness, blocking and stratification, relevance and robustness, forward and reverse causal inference, intention to treat and per protocol analyses, and potential outcomes and counterfactuals.

Sample size determination for adaptive crossover trial in detecting gene-drug interactions

Parallel design and crossover design are two of the most frequently used designs for studying drug-gene interactions. Due to the concerns of statistical power and ethics, it is often more prudent to use the crossover design while allowing the patients to have choices of not switching the treatment if the first stage treatment is effective. This complicates the calculation of the required sample size to achieve pre-specified statistical power. We propose a method to determine the required sample size with a closed-form formula. The proposed approach is applied to determine the sample size of an adaptive crossover trial in studying gene-drug interaction in treating atrial fibrillation, the most common cardiac arrhythmia in clinical practice. Our simulation study confirms the power achieved by the sample size determined using the proposed approach. Issues related to the adaptive crossover trial are also discussed and practical guidelines are provided.

Outcome trajectory estimation for optimal dynamic treatment regimes with repeated measures

In recent sequential multiple assignment randomized trials, outcomes were assessed multiple times to evaluate longer-term impacts of the dynamic treatment regimes (DTRs). Q-learning requires a scalar response to identify the optimal DTR. Inverse probability weighting may be used to estimate the optimal outcome trajectory, but it is inefficient, susceptible to model mis-specification, and unable to characterize how treatment effects manifest over time. We propose modified Q-learning with generalized estimating equations to address these limitations and apply it to the M-bridge trial, which evaluates adaptive interventions to prevent problematic drinking among college freshmen. Simulation studies demonstrate our proposed method improves efficiency and robustness.

Bayesian causal inference: a critical review

This paper provides a critical review of the Bayesian perspective of causal inference based on the potential outcomes framework. We review the causal estimands, assignment mechanism, the general structure of Bayesian inference of causal effects and sensitivity analysis. We highlight issues that are unique to Bayesian causal inference, including the role of the propensity score, the definition of identifiability, the choice of priors in both low- and high-dimensional regimes. We point out the central role of covariate overlap and more generally the design stage in Bayesian causal inference. We extend the discussion to two complex assignment mechanisms: instrumental variable and time-varying treatments. We identify the strengths and weaknesses of the Bayesian approach to causal inference. Throughout, we illustrate the key concepts via examples. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient's pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN's RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

A novel approach to assess dynamic treatment regimes embedded in a SMART with an ordinal outcome

Sequential multiple assignment randomized trials (SMARTs) are used to construct data-driven optimal intervention strategies for subjects based on their intervention and covariate histories in different branches of health and behavioral sciences where a sequence of interventions is given to a participant. Sequential intervention strategies are often called dynamic treatment regimes (DTR). In the existing literature, the majority of the analysis methodologies for SMART data assume a continuous primary outcome. However, ordinal outcomes are also quite common in clinical practice. In this work, first, we introduce the notion of generalized odds ratio ( G O R $$ GOR $$ ) to compare two DTRs embedded in a SMART with an ordinal outcome and discuss some combinatorial properties of this measure. Next, we propose a likelihood-based approach to estimate G O R $$ GOR $$ from SMART data, and derive the asymptotic properties of its estimate. We discuss alternative ways to estimate G O R $$ GOR $$ using concordant-discordant pairs and two-sample U $$ U $$ -statistic. We derive the required sample size formula for designing SMARTs with ordinal outcomes based on G O R $$ GOR $$ . A simulation study shows the performance of the estimated G O R $$ GOR $$ in terms of the estimated power corresponding to the derived sample size. The methodology is applied to analyze data from the SMART+ study, conducted in the UK, to improve carbohydrate periodization behavior in athletes using a menu planner mobile application, Hexis Performance. A freely available Shiny web app using R is provided to make the proposed methodology accessible to other researchers and practitioners.

Common statistical concepts in the supervised Machine Learning arena

One of the core elements of Machine Learning (ML) is statistics and its embedded foundational rules and without its appropriate integration, ML as we know would not exist. Various aspects of ML platforms are based on statistical rules and most notably the end results of the ML model performance cannot be objectively assessed without appropriate statistical measurements. The scope of statistics within the ML realm is rather broad and cannot be adequately covered in a single review article. Therefore, here we will mainly focus on the common statistical concepts that pertain to supervised ML (i.e. classification and regression) along with their interdependencies and certain limitations.

Reinforcement learning strategies in cancer chemotherapy treatments: A review

BACKGROUND AND OBJECTIVE

Cancer is one of the major causes of death worldwide and chemotherapies are the most significant anti-cancer therapy, in spite of the emerging precision cancer medicines in the last 2 decades. The growing interest in developing the effective chemotherapy regimen with optimal drug dosing schedule to benefit the clinical cancer patients has spawned innovative solutions involving mathematical modeling since the chemotherapy regimens are administered cyclically until the futility or the occurrence of intolerable adverse events. Thus, in this present work, we reviewed the emerging trends involved in forming a computational solution from the aspect of reinforcement learning.

METHODS

Initially, this survey in-depth focused on the details of the dynamic treatment regimens from a broad perspective and then narrowed down to inspirations from reinforcement learning that were advantageous to chemotherapy dosing, including both offline reinforcement learning and supervised reinforcement learning.

RESULTS

The insights established in the chemotherapy-planning problem associated with the Reinforcement Learning (RL) has been discussed in this study. It showed that the researchers were able to widen their perspectives in comprehending the theoretical basis, dynamic treatment regimens (DTR), use of the adaptive control on DTR, and the associated RL techniques.

CONCLUSIONS

This study reviewed the recent researches relevant to the topic, and highlighted the challenges, open questions, possible solutions, and future steps in inventing a realistic solution for the aforementioned problem.

Using Pilot Data for Power Analysis of Observational Studies for the Estimation of Dynamic Treatment Regimes

Significant attention has been given to developing data-driven methods for tailoring patient care based on individual patient characteristics. Dynamic treatment regimes formalize this approach through a sequence of decision rules that map patient information to a suggested treatment. The data for estimating and evaluating treatment regimes are ideally gathered through the use of Sequential Multiple Assignment Randomized Trials (SMARTs), though longitudinal observational studies are commonly used due to the potentially prohibitive costs of conducting a SMART. Observational studies are typically powered for simple comparisons of fixed treatment sequences; a priori power or sample size calculations for tailored strategies are rarely if ever undertaken. This has lead to many studies that fail to find a statistically significant benefit to tailoring treatment. We develop power analyses for the estimation of dynamic treatment regimes from observational studies. Our approach uses pilot data to estimate the power for comparing the value of the optimal regime, i.e., the expected outcome if all patients in the population were treated by following the optimal regime, with a known comparison mean. This allows for calculations that ensure a study has sufficient power to detect the need for tailoring, should it be present. Our approach also ensures the value of the estimated optimal treatment regime has a high probability of being within a range of the value of the true optimal regime, set a priori. We examine the performance of the proposed procedure with a simulation study and use it to size a study for reducing depressive symptoms using data from electronic health records.

Use of Sequential Multiple Assignment Randomized Trials (SMARTs) in oncology: systematic review of published studies

Sequential multiple assignments randomized trials (SMARTs) are a type of experimental design where patients may be randomised multiple times according to pre-specified decision rules. The present work investigates the state-of-the-art of SMART designs in oncology, focusing on the discrepancy between the available methodological approaches in the statistical literature and the procedures applied within cancer clinical trials. A systematic review was conducted, searching PubMed, Embase and CENTRAL for protocols or reports of results of SMART designs and registrations of SMART designs in clinical trial registries applied to solid tumour research. After title/abstract and full-text screening, 33 records were included. Fifteen were reports of trials' results, four were trials' protocols and fourteen were trials' registrations. The study design was defined as SMART by only one out of fifteen trial reports. Conversely, 13 of 18 study protocols and trial registrations defined the study design SMART. Furthermore, most of the records considered each stage separately in the analysis, without considering treatment regimens embedded in the trial. SMART designs in oncology are still limited. Study powering and analysis is mainly based on statistical approaches traditionally used in single-stage parallel trial designs. Formal reporting guidelines for SMART designs are needed.

Projection based inverse reinforcement learning for the analysis of dynamic treatment regimes

Dynamic Treatment Regimes (DTRs) are adaptive treatment strategies that allow clinicians to personalize dynamically the treatment for each patient based on their step-by-step response to their treatment. There are a series of predefined alternative treatments for each disease and any patient may associate with one of these treatments according to his/her demographics. DTRs for a certain disease are studied and evaluated by means of statistical approaches where patients are randomized at each step of the treatment and their responses are observed. Recently, the Reinforcement Learning (RL) paradigm has also been applied to determine DTRs. However, such approaches may be limited by the need to design a true reward function, which may be difficult to formalize when the expert knowledge is not well assessed, as when the DTR is in the design phase. To address this limitation, an extension of the RL paradigm, namely Inverse Reinforcement Learning (IRL), has been adopted to learn the reward function from data, such as those derived from DTR trials. In this paper, we define a Projection Based Inverse Reinforcement Learning (PB-IRL) approach to learn the true underlying reward function for given demonstrations (DTR trials). Such a reward function can be used both to evaluate the set of DTRs determined for a certain disease, as well as to enable an RL-based intelligent agent to self-learn the best way and then act as a decision support system for the clinician.

A Comparison of Methods for Treatment Assignment with an Application to Playlist Generation

This study presents a systematic comparison of methods for individual treatment assignment. We group the various methods proposed in the literature into three general classes of algorithms (or metalearners): learning models to predict outcomes (the O-learner), learning models to predict causal effects (the E-learner), and learning models to predict optimal treatment assignments (the A-learner). We discuss how the metalearners differ in their level of generality and their objective function, which has critical implications for modeling and decision making. Notably, we demonstrate that optimizing for the prediction of outcomes or causal effects is not the same as optimizing for treatment assignments, suggesting that, in general, the A-learner should lead to better treatment assignments than the other metalearners. We then compare the metalearners in the context of choosing, for each user, the best algorithm for playlist generation in order to optimize engagement. This is the first comparison of the three different metalearners on a real-world application at scale (based on more than half a billion treatment assignments). In addition to supporting our analytical findings, the results show how large A/B tests can provide substantial value for learning treatment-assignment policies, rather than simply choosing the variant that performs best on average.

Optimizing the dynamic treatment regime of in-hospital warfarin anticoagulation in patients after surgical valve replacement using reinforcement learning

OBJECTIVE

Warfarin anticoagulation management requires sequential decision-making to adjust dosages based on patients' evolving states continuously. We aimed to leverage reinforcement learning (RL) to optimize the dynamic in-hospital warfarin dosing in patients after surgical valve replacement (SVR).

MATERIALS AND METHODS

10 408 SVR cases with warfarin dosage-response data were retrospectively collected to develop and test an RL algorithm that can continuously recommend daily warfarin doses based on patients' evolving multidimensional states. The RL algorithm was compared with clinicians' actual practice and other machine learning and clinical decision rule-based algorithms. The primary outcome was the ratio of patients without in-hospital INRs >3.0 and the INR at discharge within the target range (1.8-2.5) (excellent responders). The secondary outcomes were the safety responder ratio (no INRs >3.0) and the target responder ratio (the discharge INR within 1.8-2.5).

RESULTS

In the test set (n = 1260), the excellent responder ratio under clinicians' guidance was significantly lower than the RL algorithm: 41.6% versus 80.8% (relative risk [RR], 0.51; 95% confidence interval [CI], 0.48-0.55), also the safety responder ratio: 83.1% versus 99.5% (RR, 0.83; 95% CI, 0.81-0.86), and the target responder ratio: 49.7% versus 81.1% (RR, 0.61; 95% CI, 0.58-0.65). The RL algorithms performed significantly better than all the other algorithms. Compared with clinicians' actual practice, the RL-optimized INR trajectory reached and maintained within the target range significantly faster and longer.

DISCUSSION

RL could offer interactive, practical clinical decision support for sequential decision-making tasks and is potentially adaptable for varied clinical scenarios. Prospective validation is needed.

CONCLUSION

An RL algorithm significantly optimized the post-operation warfarin anticoagulation quality compared with clinicians' actual practice, suggesting its potential for challenging sequential decision-making tasks.

Machine Learning Methods in Health Economics and Outcomes Research-The PALISADE Checklist: A Good Practices Report of an ISPOR Task Force

Advances in machine learning (ML) and artificial intelligence offer tremendous potential benefits to patients. Predictive analytics using ML are already widely used in healthcare operations and care delivery, but how can ML be used for health economics and outcomes research (HEOR)? To answer this question, ISPOR established an emerging good practices task force for the application of ML in HEOR. The task force identified 5 methodological areas where ML could enhance HEOR: (1) cohort selection, identifying samples with greater specificity with respect to inclusion criteria; (2) identification of independent predictors and covariates of health outcomes; (3) predictive analytics of health outcomes, including those that are high cost or life threatening; (4) causal inference through methods, such as targeted maximum likelihood estimation or double-debiased estimation-helping to produce reliable evidence more quickly; and (5) application of ML to the development of economic models to reduce structural, parameter, and sampling uncertainty in cost-effectiveness analysis. Overall, ML facilitates HEOR through the meaningful and efficient analysis of big data. Nevertheless, a lack of transparency on how ML methods deliver solutions to feature selection and predictive analytics, especially in unsupervised circumstances, increases risk to providers and other decision makers in using ML results. To examine whether ML offers a useful and transparent solution to healthcare analytics, the task force developed the PALISADE Checklist. It is a guide for balancing the many potential applications of ML with the need for transparency in methods development and findings.

Effects of a continuous nursing care model on elderly patients with total hip arthroplasty: a randomized controlled trial

BACKGROUND

Continuous nursing care (CNC) is an extended service based on meeting the needs of discharged patients for post-discharge treatment and rehabilitation. This research aimed to investigate the effects of CNC on older patients with total hip arthroplasty and to offer a scientific basis for improving the prognosis.

METHODS

A total of 134 patients with total hip arthroplasty were randomly divided into the control group (n = 67) and the intervention group (n = 67). The control group was treated by conventional nursing care and the intervention group was treated by CNC. Harris hip score, Barthel index, the activities of daily living (ADL) scale, self-rating depression scale (SDS) and self-rating anxiety scale (SAS) in these two groups were evaluated. Demographic characteristics between groups were analyzed by unpaired t test. The observation indexes between groups were assessed by two-way ANOVA test followed by Tukey's multiple comparisons test.

RESULTS

The scores of Harris hip score, Barthel index, ADL, SDS and SAS in the intervention group after intervention and after follow-up were better than the intervention group before intervention (all p < 0.01). Meanwhile, the scores of Harris hip score, Barthel index, ADL, SDS and SAS in the intervention group were better than the control group both after intervention and after follow-up (all p < 0.01).

CONCLUSION

In conclusion, CNC showed better efficacy than conventional nursing care in promoting hip joint function recovery, improving quality of life and alleviating anxiety and depression for older patients with total hip arthroplasty.

Estimators for the value of the optimal dynamic treatment rule with application to criminal justice interventions

Given an (optimal) dynamic treatment rule, it may be of interest to evaluate that rule - that is, to ask the causal question: what is the expected outcome had every subject received treatment according to that rule? In this paper, we study the performance of estimators that approximate the true value of: (1) an a priori known dynamic treatment rule (2) the true, unknown optimal dynamic treatment rule (ODTR); (3) an estimated ODTR, a so-called "data-adaptive parameter," whose true value depends on the sample. Using simulations of point-treatment data, we specifically investigate: (1) the impact of increasingly data-adaptive estimation of nuisance parameters and/or of the ODTR on performance; (2) the potential for improved efficiency and bias reduction through the use of semiparametric efficient estimators; and, (3) the importance of sample splitting based on the cross-validated targeted maximum likelihood estimator (CV-TMLE) for accurate inference. In the simulations considered, there was very little cost and many benefits to using CV-TMLE to estimate the value of the true and estimated ODTR; importantly, and in contrast to non cross-validated estimators, the performance of CV-TMLE was maintained even when highly data-adaptive algorithms were used to estimate both nuisance parameters and the ODTR. In addition, we apply these estimators for the value of the rule to the "Interventions" study, an ongoing randomized controlled trial, to identify whether assigning cognitive behavioral therapy (CBT) to criminal justice-involved adults with mental illness using an ODTR significantly reduces the probability of recidivism, compared to assigning CBT in a non-individualized way.

"On a night like this": A mixed-methods approach to understanding high-risk drinking events in college students

BACKGROUND

Previous research indicates college students report heavier drinking on certain events (e.g., 21st birthday). While past research has identified heavier drinking events, students' own reports of which events are associated with elevated drinking remains understudied. The current study utilized mixed methods to explore potential high-risk drinking events (HRDE) for college student drinkers and how these events differed from typical drinking and each other.

METHODS

College student drinkers (N = 204) reported the number of drinks they consume on nine predetermined events (e.g., Halloween). Students also responded to open-ended questions listing five events during which they had elevated drinking and indicating the amount consumed on each event. Open-ended responses were coded into similar event categories. Descriptive statistics for drinks consumed were calculated for predetermined and coded open-ended events. Chi-square analyses assessed differences in endorsement of open-ended events by birth sex, age group, and Greek membership. Two multilevel count regressions assessed within-person differences in number of drinks consumed between participants' typical drinking occasions and (1) highly endorsed open-ended events and (2) predetermined events.

RESULTS

For all open-ended event categories, average number of drinks consumed exceeded heavy episodic drinking thresholds; however, there was substantial variability. Comparing predetermined events to participants' typical drinking indicated elevated drinking on participants' birthdays, New Year's Eve, Halloween, Finals, and Spring Break; significant differences between events also emerged. Comparison of open-ended categories to participants' typical drinking indicated elevated drinking on birthdays, celebrations, parties, and holidays; however, there were no significant differences between open-ended events.

CONCLUSIONS

Students who drink alcohol report heavier drinking on specific calendar-based events (e.g., Spring Break). However, students also report non-calendar-related events (e.g., non-specific parties) as some of their highest drinking events. More research is needed to understand how intervention and prevention programs can be adapted to target both known calendar-based HRDE, and unknown, idiosyncratic HRDE.

Optimal dynamic treatment regime estimation using information extraction from unstructured clinical text

The wide-scale adoption of electronic health records (EHRs) provides extensive information to support precision medicine and personalized health care. In addition to structured EHRs, we leverage free-text clinical information extraction (IE) techniques to estimate optimal dynamic treatment regimes (DTRs), a sequence of decision rules that dictate how to individualize treatments to patients based on treatment and covariate history. The proposed IE of patient characteristics closely resembles "The clinical Text Analysis and Knowledge Extraction System" and employs named entity recognition, boundary detection, and negation annotation. It also utilizes regular expressions to extract numerical information. Combining the proposed IE with optimal DTR estimation, we extract derived patient characteristics and use tree-based reinforcement learning (T-RL) to estimate multistage optimal DTRs. IE significantly improved the estimation in counterfactual outcome models compared to using structured EHR data alone, which often include incomplete data, data entry errors, and other potentially unobserved risk factors. Moreover, including IE in optimal DTR estimation provides larger study cohorts and a broader pool of candidate tailoring variables. We demonstrate the performance of our proposed method via simulations and an application using clinical records to guide blood pressure control treatments among critically ill patients with severe acute hypertension. This joint estimation approach improves the accuracy of identifying the optimal treatment sequence by 14-24% compared to traditional inference without using IE, based on our simulations over various scenarios. In the blood pressure control application, we successfully extracted significant blood pressure predictors that are unobserved or partially missing from structured EHR.

Novel Use of Patient-Specific Covariates From Oncology Studies in the Era of Biomedical Data Science: A Review of Latest Methodologies

In this article, we review different applications of how to incorporate individual patient variables into clinical research within oncology. These methodologies range from the more traditional use of baseline covariates from randomized clinical trials, as well as observational studies, to using covariates to generalize the results of randomized clinical trials to other populations. Individual patient variables also allow for the consideration of heterogeneity in treatment effects and individualized treatment rules. We primarily consider two treatment groups and mostly focus on time-to-event outcomes where such methodologies have been well established and widely applied. We also discuss more conceptually newer statistical research that has not been widely applied in clinical oncology, but is likely to make an impact in future oncology research. With the increasing amount of biomedical data available for analysis, it is inevitable that more methods are developed to make best use of information, to advance oncology research.

Association between dynamic dose increases of buprenorphine for treatment of opioid use disorder and risk of relapse

BACKGROUND AND AIMS

Dynamic, adaptive pharmacologic treatment for opioid use disorder (OUD) has been previously recommended over static dosing to prevent relapse, and is aligned with personalized medicine. However, there has been no quantitative evidence demonstrating its advantage. Our objective was to estimate the extent to which a hypothetical intervention that increased buprenorphine dose in response to opioid use would affect risk of relapse over 24 weeks of follow-up.

DESIGN

A secondary analysis of the buprenorphine arm of an open-label randomized controlled 24-week comparative effectiveness trial, 2014-17.

SETTING

Eight community addiction treatment programs in the United States.

PARTICIPANTS

English-speaking adults with DSM-5 OUD, recruited during inpatient admission (n = 270). Participants were mainly white (65%) and male (72%).

INTERVENTION(S)

Participants were treated with daily sublingual buprenorphine-naloxone (BUP-NX), with dose based on clinical indication, determined by the provider. We examined a hypothetical intervention of increasing dose in response to opioid use.

MEASUREMENTS

Outcome was relapse to regular opioid use during the 24 weeks of outpatient treatment, assessed in a survival framework. We estimated the relapse-free survival curves of participants under a hypothetical (i.e. counterfactual) intervention in which their BUP-NX dosage would be increased following their own subject-specific opioid use during the first 12 weeks of treatment versus a hypothetical intervention in which dose would remain constant.

FINDINGS

We estimated that increasing BUP-NX dose in response to recent opioid use would lower risk of relapse by 19.17 percentage points [95% confidence interval (CI) = -32.17, -6.18) (additive risk)] and 32% (0.68, 95% CI = 0.49, 0.86) (relative risk). The number-needed-to-treat with this intervention to prevent a single relapse is 6.

CONCLUSIONS

In people with opioid use disorder, a hypothetical intervention that increases sublingual buprenorphine-naloxone dose in response to opioid use during the first 12 weeks of treatment appears to reduce risk of relapse over 24 weeks, compared with holding the dose constant after week 2.

Personalized next-best action recommendation with multi-party interaction learning for automated decision-making

Automated next-best action recommendation for each customer in a sequential, dynamic and interactive context has been widely needed in natural, social and business decision-making. Personalized next-best action recommendation must involve past, current and future customer demographics and circumstances (states) and behaviors, long-range sequential interactions between customers and decision-makers, multi-sequence interactions between states, behaviors and actions, and their reactions to their counterpart’s actions. No existing modeling theories and tools, including Markovian decision processes, user and behavior modeling, deep sequential modeling, and personalized sequential recommendation, can quantify such complex decision-making on a personal level. We take a data-driven approach to learn the next-best actions for personalized decision-making by a reinforced coupled recurrent neural network (CRN). CRN represents multiple coupled dynamic sequences of a customer’s historical and current states, responses to decision-makers’ actions, decision rewards to actions, and learns long-term multi-sequence interactions between parties (customer and decision-maker). Next-best actions are then recommended on each customer at a time point to change their state for an optimal decision-making objective. Our study demonstrates the potential of personalized deep learning of multi-sequence interactions and automated dynamic intervention for personalized decision-making in complex systems.

Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven study

BACKGROUND

Coronary heart disease (CHD) has become the leading cause of death and one of the most serious epidemic diseases worldwide. CHD is characterized by urgency, danger and severity, and dynamic treatment strategies for CHD patients are needed. We aimed to build and validate an AI model for dynamic treatment recommendations for CHD patients with the goal of improving patient outcomes and learning best practices from clinicians to help clinical decision support for treating CHD patients.

METHODS

We formed the treatment strategy as a sequential decision problem, and applied an AI supervised reinforcement learning-long short-term memory (SRL-LSTM) framework that combined supervised learning (SL) and reinforcement learning (RL) with an LSTM network to track patients' states to learn a recommendation model that took a patient's diagnosis and evolving health status as input and provided a treatment recommendation in the form of whether to take specific drugs. The experiments were conducted by leveraging a real-world intensive care unit (ICU) database with 13,762 admitted patients diagnosed with CHD. We compared the performance of the applied SRL-LSTM model and several state-of-the-art SL and RL models in reducing the estimated in-hospital mortality and the Jaccard similarity with clinicians' decisions. We used a random forest algorithm to calculate the feature importance of both the clinician policy and the AI policy to illustrate the interpretability of the AI model.

RESULTS

Our experimental study demonstrated that the AI model could help reduce the estimated in-hospital mortality through its RL function and learn the best practice from clinicians through its SL function. The similarity between the clinician policy and the AI policy regarding the surviving patients was high, while for the expired patients, it was much lower. The dynamic treatment strategies made by the AI model were clinically interpretable and relied on sensible clinical features extracted according to monitoring indexes and risk factors for CHD patients.

CONCLUSIONS

We proposed a pipeline for constructing an AI model to learn dynamic treatment strategies for CHD patients that could improve patient outcomes and mimic the best practices of clinicians. And a lot of further studies and efforts are needed to make it practical.

Step-adjusted tree-based reinforcement learning for evaluating nested dynamic treatment regimes using test-and-treat observational data

Dynamic treatment regimes (DTRs) include a sequence of treatment decision rules, in which treatment is adapted over time in response to the changes in an individual's disease progression and health care history. In medical practice, nested test-and-treat strategies are common to improve cost-effectiveness. For example, for patients at risk of prostate cancer, only patients who have high prostate-specific antigen (PSA) need a biopsy, which is costly and invasive, to confirm the diagnosis and help determine the treatment if needed. A decision about treatment happens after the biopsy, and is thus nested within the decision of whether to do the test. However, current existing statistical methods are not able to accommodate such a naturally embedded property of the treatment decision within the test decision. Therefore, we developed a new statistical learning method, step-adjusted tree-based reinforcement learning, to evaluate DTRs within such a nested multistage dynamic decision framework using observational data. At each step within each stage, we combined the robust semiparametric estimation via augmented inverse probability weighting with a tree-based reinforcement learning method to deal with the counterfactual optimization. The simulation studies demonstrated robust performance of the proposed methods under different scenarios. We further applied our method to evaluate the necessity of prostate biopsy and identify the optimal test-and-treat regimes for prostate cancer patients using data from the Johns Hopkins University prostate cancer active surveillance dataset.

Sequential multiple assignment randomized trial studies should report all key components: a systematic review

OBJECTIVE

Sequential Multiple Assignment Randomised Trial (SMART) designs allow multiple randomisations of participants; this allows assessment of stage-specific questions (individual randomisations) and adaptive interventions (i.e. treatment strategies). We assessed the quality of reporting of the information required to design SMART studies.

STUDY DESIGN AND SETTING

We systematically searched four databases (PubMed, Ovid, Web of Science and Scopus) for all trial reports, protocols, reviews, and methodological papers which mentioned SMART designs up to June 15, 2020.

RESULTS

Of the 157 selected records, 12 (7.64%) were trial reports, 24 (15.29%) were study protocols, 91 (58%) were methodological papers, and 30 (19.1%) were review papers. All these trials were powered using stage-specific aims. Only four (33.33%) of these trials reported parameters required for sample size calculations. A small number of the trials (16.67 %) were interested in determining the best embedded adaptive interventions. Most of the trials did not report information about multiple testing adjustment. Furthermore, most of records reported designs that were mainly focused on stage-specific aims.

CONCLUSIONS

Some features of SMART designs are seldomly reported and/or used. Furthermore, studies using this design tend to not adequately report information about all the design parameters, limiting their transparency and interpretability.

Multitiered Systems of Support, Adaptive Interventions, and SMART Designs

This article introduces the special section on adaptive interventions and sequential multiple-assignment randomized trial (SMART) research designs. In addition to describing the two accompanying articles, we discuss features of adaptive interventions (AIs) and describe the use of SMART design to optimize AIs in the context of multitiered systems of support (MTSS) and integrated MTSS. AI is a treatment delivery model that explicitly specifies how information about individuals should be used to decide which treatment to provide in practice. Principles that apply to the design of AIs may help to more clearly operationalize MTSS-based programs, improve their implementation in school settings, and increase their efficacy when used according to evidence-based decision rules. A SMART is a research design for developing and optimizing MTSS-based programs. We provide a running example of a SMART design to optimize an MTSS-aligned AI that integrates academic and behavioral interventions.