Explore the vast range of titles available.

Adaptive combination therapy is deemed the most intuitive strategy to thwart therapeutic resistance through dynamic treatment tuning that accounts for cancer evolutionary dynamics. However, higher accuracy and reliability of treatment response predictions would be needed, in addition to the need for clinically feasible models of adaptive combination therapy that consider newly approved therapeutics and the growing multimodal data being available about cancer. Grounded in nonlinear system control theory, this review offers a perspective on exploiting GenAI learning and inferencing capabilities to predict treatment response and recommend treatments in the context of adaptive cancer therapy. Results from nonlinear system identification, control theory and deep learning are integrated within an adaptive cancer control framework to leverage the continuously expanding data about cancer and its treatment towards GenAI-enhanced adaptive therapy. The resulting models and their analysis contribute to a much-needed conceptual clarity about the research and translational pathways that would be needed to realize GenAI-assisted cancer treatments. In particular, they underscore that access to clinical data, deep learning opacity, and clinical validation present critical challenges that require adequate attention to pave the way towards acceptance and integration of GenAI in real-world oncology workflows. Plain Language Summary Despite the increasing number of treatment options being available to cancer patients, most of these treatments stop working after some time due to the cancer becoming resistant. One of the strategies to thwart cancer resistance is to design treatments that are one-step-ahead of cancer by using drug combinations and adapting therapies based on treatment response monitoring. This treatment approach is called adaptive therapy. This study explores the use of generative artificial intelligence (GenAI) models to enhance adaptive therapy by predicting changes of the disease and accordingly adapting treatments based on learning acquired by these models through training on large amount of data about cancer and patient treatments. The study highlights a pathway for the clinical evaluation of this GenAI-assisted approach to cancer therapy and discusses the challenges associated with its implementation and deployment in clinics.

•A Sequential Multiple Assignment Randomized Trial (SMART) is a design that involves multiple stages of randomization. Patient's characteristics and treatment history are used to re-randomize them. Many clinically important questions can be answered using SMART designs.•Studies using SMART design do not always adequately report information about all the design parameters.•Some appealing features of the SMART design are rarely used.•Information about: primary aims (stage-specific aims, AIs related aims), sample size calculation, analyses considerations should always be reported. Sequential Multiple Assignment Randomized Trial (SMART) designs allow multiple randomizations of participants; this allows assessment of stage-specific questions (individual randomizations) and adaptive interventions (i.e. treatment strategies). We assessed the quality of reporting of the information required to design SMART studies. 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. 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. 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.

Decision-makers increasingly have access to rich customer-specific data, providing an opportunity to make better, personalized service decisions. For example, in healthcare, doctors can personalize interventions based on a patient’s clinical history; in marketing, companies can target ads based on customer purchase history. However, the increased variety of potentially relevant customer data implies that an individual’s covariates may be high dimensional , which, in turn, poses statistical challenges for learning personalized decision-making policies. In “Online Decision-Making with High-Dimensional Covariates,” H. Bastani and M. Bayati introduce the LASSO Bandit, an adaptive decision-making algorithm that efficiently leverages high-dimensional user covariates by learning sparse models of decision rewards. The authors illustrate the practical relevance of such an approach by evaluating it against a personalized medication dosing problem, finding that the LASSO Bandit outperforms existing bandit methods and physicians in correctly dosing a majority of patients. Big data have enabled decision makers to tailor decisions at the individual level in a variety of domains, such as personalized medicine and online advertising. Doing so involves learning a model of decision rewards conditional on individual-specific covariates. In many practical settings, these covariates are high dimensional ; however, typically only a small subset of the observed features are predictive of a decision’s success. We formulate this problem as a K -armed contextual bandit with high-dimensional covariates and present a new efficient bandit algorithm based on the LASSO estimator. We prove that our algorithm’s cumulative expected regret scales at most polylogarithmically in the covariate dimension d ; to the best of our knowledge, this is the first such bound for a contextual bandit. The key step in our analysis is proving a new tail inequality that guarantees the convergence of the LASSO estimator despite the non-i.i.d. data induced by the bandit policy. Furthermore, we illustrate the practical relevance of our algorithm by evaluating it on a simplified version of a medication dosing problem. A patient’s optimal medication dosage depends on the patient’s genetic profile and medical records; incorrect initial dosage may result in adverse consequences, such as stroke or bleeding. We show that our algorithm outperforms existing bandit methods and physicians in correctly dosing a majority of patients.

Background Online adaptive radiotherapy has the potential to reduce toxicity for patients treated for rectal cancer because smaller planning target volumes (PTV) margins around the entire clinical target volume (CTV) are required. The aim of this study is to describe the first clinical experience of a Conebeam CT (CBCT)-based online adaptive workflow for rectal cancer, evaluating timing of different steps in the workflow, plan quality, target coverage and patient compliance. Methods Twelve consecutive patients eligible for 5 × 5 Gy pre-operative radiotherapy were treated on a ring-based linear accelerator with a multidisciplinary team present at the treatment machine for each fraction. The accelerator is operated using an integrated software platform for both treatment planning and delivery. In all directions for all CTVs a PTV margin of 5 mm was used, except for the cranial/caudal borders of the total CTV where a margin of 8 mm was applied. A reference plan was generated based on a single planning CT. After aligning the patient the online adaptive procedure started with acquisition of a CBCT. The planning CT scan was registered to the CBCT using deformable registration and a synthetic CT scan was generated. With the support of artificial intelligence, structure guided deformation and the synthetic CT scan contours were adapted by the system to match the anatomy on the CBCT. If necessary, these contours were adjusted before a new plan was generated. A second and third CBCT were acquired to validate the new plan with respect to CTV coverage just before and after treatment delivery, respectively. Treatment was delivered using volumetric modulated arc treatment (VMAT). All steps in this process were defined and timed. Results On average the timeslot needed at the treatment machine was 34 min. The process of acquiring a CBCT, evaluating and adjusting the contours, creating the new plan and verifying the CTV on the CBCT scan took on average 20 min. Including delivery and post treatment verification this was 26 min. Manual adjustments of the target volumes were necessary in 50% of fractions. Plan quality, target coverage and patient compliance were excellent. Conclusions First clinical experience with CBCT-based online adaptive radiotherapy shows it is feasible for rectal cancer. Trial registration Medical Research Involving Human Subjects Act (WMO) does not apply to this study and was retrospectively approved by the Medical Ethics review Committee of the Academic Medical Center (W21_087 # 21.097; Amsterdam University Medical Centers, Location Academic Medical Center, Amsterdam, The Netherlands).

Background: Internet-delivered psychological treatments (IDPTs) are built on evidence-based psychological treatment models, such as cognitive behavioral therapy, and are adjusted for internet use. The use of internet technologies has the potential to increase access to evidence-based mental health services for a larger proportion of the population with the use of fewer resources. However, despite extensive evidence that internet interventions can be effective in the treatment of mental health disorders, user adherence to such internet intervention is suboptimal. Objective: This review aimed to (1) inspect and identify the adaptive elements of IDPT for mental health disorders, (2) examine how system adaptation influences the efficacy of IDPT on mental health treatments, (3) identify the information architecture, adaptive dimensions, and strategies for implementing these interventions for mental illness, and (4) use the findings to create a conceptual framework that provides better user adherence and adaptiveness in IDPT for mental health issues. Methods: The review followed the guidelines from Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). The research databases Medline (PubMed), ACM Digital Library, PsycINFO, CINAHL, and Cochrane were searched for studies dating from January 2000 to January 2020. Based on predetermined selection criteria, data from eligible studies were analyzed. Results: A total of 3341 studies were initially identified based on the inclusion criteria. Following a review of the title, abstract, and full text, 31 studies that fulfilled the inclusion criteria were selected, most of which described attempts to tailor interventions for mental health disorders. The most common adaptive elements were feedback messages to patients from therapists and intervention content. However, how these elements contribute to the efficacy of IDPT in mental health were not reported. The most common information architecture used by studies was tunnel-based, although a number of studies did not report the choice of information architecture used. Rule-based strategies were the most common adaptive strategies used by these studies. All of the studies were broadly grouped into two adaptive dimensions based on user preferences or using performance measures, such as psychometric tests. Conclusions: Several studies suggest that adaptive IDPT has the potential to enhance intervention outcomes and increase user adherence. There is a lack of studies reporting design elements, adaptive elements, and adaptive strategies in IDPT systems. Hence, focused research on adaptive IDPT systems and clinical trials to assess their effectiveness are needed.

The management of many health disorders often entails a sequential, individualized approach whereby treatment is adapted and readapted over time in response to the specific needs and evolving status of the individual. Adaptive interventions provide one way to operationalize the strategies (e.g., continue, augment, switch, step-down) leading to individualized sequences of treatment. Often, a wide variety of critical questions must be answered when developing a high-quality adaptive intervention. Yet, there is often insufficient empirical evidence or theoretical basis to address these questions. The Sequential Multiple Assignment Randomized Trial (SMART)—a type of research design—was developed explicitly for the purpose of building optimal adaptive interventions by providing answers to such questions. Despite increasing popularity, SMARTs remain relatively new to intervention scientists. This manuscript provides an introduction to adaptive interventions and SMARTs. We discuss SMART design considerations, including common primary and secondary aims. For illustration, we discuss the development of an adaptive intervention for optimizing weight loss among adult individuals who are overweight.

Background To compare online adaptive radiation therapy (ART) to a clinically implemented plan selection strategy (PS) with respect to dose to the organs at risk (OAR) for rectal cancer. Methods The first 20 patients treated with PS between May–September 2016 were included. This resulted in 10 short (SCRT) and 10 long (LCRT) course radiotherapy treatment schedules with a total of 300 Conebeam CT scans (CBCT). New dual arc VMAT plans were generated using auto-planning for both the online ART and PS strategy. For each fraction bowel bag, bladder and mesorectum were delineated on daily Conebeam CTs. The dose distribution planned was used to calculate daily DVHs. Coverage of the CTV was calculated, as defined by the dose received by 99% of the CTV volume (D99%). The volume of normal tissue irradiated with 95% of the prescribed fraction dose was calculated by calculating the volume receiving 95% of the prescribed fraction or more dose minus the volume of the CTV. For each fraction the difference between the plan selection and online adaptive strategy of each DVH parameter was calculated, as well as the average difference per patient. Results Target coverage remained the same for online ART. The median volume of the normal tissue irradiated with 95% of the prescribed dose dropped from 642 cm3 (PS) to 237 cm3 (online-ART)( p  < 0.001). Online ART reduced dose to the OARs for all tested dose levels for SCRT and LCRT ( p  < 0.001). For V15Gy of the bowel bag the median difference over all fractions of all patients was − 126 cm 3 in LCRT, while the average difference per patient ranged from − 206 cm 3 to − 40 cm 3 . For SCRT the median difference was − 62 cm 3 , while the range of the average difference per patient was − 105 cm3 to − 51 cm 3 . For V15Gy of the bladder the median difference over all fractions of all patients was 26% in LCRT, while the average difference per patient ranged from − 34 to 12%. For SCRT the median difference of V95% was − 8%, while the range of the average difference per patient was − 29 to 0%. Conclusions Online ART for rectal cancer reduces dose the OARs significantly compared to a clinically implemented plan selection strategy, without compromising target coverage. Trial registration Medical Research Involving Human Subjects Act (WMO) does not apply to this study and was retrospectively approved by the Medical Ethics review Committee of the Academic Medical Center (W19_357 # 19.420; Amsterdam University Medical Centers, Location Academic Medical Center, Amsterdam, The Netherlands).

The latest developments in the management of head and neck cancer show an increasing trend in the implementation of novel approaches using artificial intelligence for better patient stratification and treatment-related risk evaluation. Radiomics, or the extraction of data from various imaging modalities, is a tool often used to evaluate specific features related to the tumour or normal tissue that are not identifiable by the naked eye and which can add value to existing clinical data. Furthermore, the assessment of feature variations from one time point to another based on subsequent images, known as delta radiomics, was shown to have even higher value for treatment-outcome prediction or patient stratification into risk categories. The information gathered from delta radiomics can, further, be used for decision making regarding treatment adaptation or other interventions found to be beneficial to the patient. The aim of this work is to collate the existing studies on delta radiomics in head and neck cancer and evaluate its role in tumour response and normal-tissue toxicity predictions alike. Moreover, this work also highlights the role of holomics, which brings under the same umbrella clinical and radiomic features, for a more complex patient characterization and treatment optimisation.

Currently available medication for treating many chronic diseases is often effective only for a subgroup of patients, and biomarkers accurately assessing whether an individual belongs to this subgroup typically do not exist. In such settings, physicians learn about the effectiveness of a drug primarily through experimentation—i.e., by initiating treatment and monitoring the patient’s response. Precise guidelines for discontinuing treatment are often lacking or left entirely to the physician’s discretion. We introduce a framework for developing adaptive, personalized treatments for such chronic diseases. Our model is based on a continuous-time, multi-armed bandit setting where drug effectiveness is assessed by aggregating information from several channels: by continuously monitoring the state of the patient, but also by (not) observing the occurrence of particular infrequent health events, such as relapses or disease flare-ups. Recognizing that the timing and severity of such events provide critical information for treatment decisions is a key point of departure in our framework compared with typical (bandit) models used in healthcare. We show that the model can be analyzed in closed form for several settings of interest, resulting in optimal policies that are intuitive and may have practical appeal. We illustrate the effectiveness of the methodology by developing a set of efficient treatment policies for multiple sclerosis, which we then use to benchmark several existing treatment guidelines. The online appendix is available at https://doi.org/10.1287/mnsc.2017.2793 . This paper was accepted by Noah Gans, stochastic models and simulation.

Background Dynamic treatment regimens (DTRs) formalise the multi-stage and dynamic decision problems that clinicians often face when treating chronic or progressive medical conditions. Compared to randomised controlled trials, using observational data to optimise DTRs may allow a wider range of treatments to be evaluated at a lower cost. This review aimed to provide an overview of how DTRs are optimised with observational data in practice. Methods Using the PubMed database, a scoping review of studies in which DTRs were optimised using observational data was performed in October 2020. Data extracted from eligible articles included target medical condition, source and type of data, statistical methods, and translational relevance of the included studies. Results From 209 PubMed abstracts, 37 full-text articles were identified, and a further 26 were screened from the reference lists, totalling 63 articles for inclusion in a narrative data synthesis. Observational DTR models are a recent development and their application has been concentrated in a few medical areas, primarily HIV/AIDS (27, 43%), followed by cancer (8, 13%), and diabetes (6, 10%). There was substantial variation in the scope, intent, complexity, and quality between the included studies. Statistical methods that were used included inverse-probability weighting (26, 41%), the parametric G-formula (16, 25%), Q-learning (10, 16%), G-estimation (4, 6%), targeted maximum likelihood/minimum loss-based estimation (4, 6%), regret regression (3, 5%), and other less common approaches (10, 16%). Notably, studies that were primarily intended to address real-world clinical questions (18, 29%) tended to use inverse-probability weighting and the parametric G-formula, relatively well-established methods, along with a large amount of data. Studies focused on methodological developments (45, 71%) tended to be more complicated and included a demonstrative real-world application only. Conclusions As chronic and progressive conditions become more common, the need will grow for personalised treatments and methods to estimate the effects of DTRs. Observational DTR studies will be necessary, but so far their use to inform clinical practice has been limited. Focusing on simple DTRs, collecting large and rich clinical datasets, and fostering tight partnerships between content experts and data analysts may result in more clinically relevant observational DTR studies.