Dataset Information

Frequencies of decision making and monitoring in adaptive resource management.

ABSTRACT: Adaptive management involves learning-oriented decision making in the presence of uncertainty about the responses of a resource system to management. It is implemented through an iterative sequence of decision making, monitoring and assessment of system responses, and incorporating what is learned into future decision making. Decision making at each point is informed by a value or objective function, for example total harvest anticipated over some time frame. The value function expresses the value associated with decisions, and it is influenced by system status as updated through monitoring. Often, decision making follows shortly after a monitoring event. However, it is certainly possible for the cadence of decision making to differ from that of monitoring. In this paper we consider different combinations of annual and biennial decision making, along with annual and biennial monitoring. With biennial decision making decisions are changed only every other year; with biennial monitoring field data are collected only every other year. Different cadences of decision making combine with annual and biennial monitoring to define 4 scenarios. Under each scenario we describe optimal valuations for active and passive adaptive decision making. We highlight patterns in valuation among scenarios, depending on the occurrence of monitoring and decision making events. Differences between years are tied to the fact that every other year a new decision can be made no matter what the scenario, and state information is available to inform that decision. In the subsequent year, however, in 3 of the 4 scenarios either a decision is repeated or monitoring does not occur (or both). There are substantive differences in optimal values among the scenarios, as well as the optimal policies producing those values. Especially noteworthy is the influence of monitoring cadence on valuation in some years. We highlight patterns in policy and valuation among the scenarios, and discuss management implications and extensions.

SUBMITTER: Williams BK

PROVIDER: S-EPMC5553789 | biostudies-other | 2017

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description: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.

Project description:As global systems rapidly change, our collective ability to predict future ecological dynamics will become increasingly important for successful natural resource management. By merging stakeholder objectives with system uncertainty, and by adapting actions to changing systems and knowledge, adaptive resource management (ARM) provides a rigorous platform for making sound decisions in a changing world. Critically, however, applications of ARM could be improved by employing benchmarks (i.e., points of reference) for determining when learning is occurring through the cycle of monitoring, modeling, and decision-making steps in ARM. Many applications of ARM use multiple model-based hypotheses to identify and reduce systematic uncertainty over time, but generally lack benchmarks for gauging discovery of scientific evidence and learning. This creates the danger of thinking that directional changes in model weights or rankings are indicative of evidence for hypotheses, when possibly all competing models are inadequate. There is thus a somewhat obvious, but yet to be filled niche for including benchmarks for learning in ARM. We contend that carefully designed "ecological null models," which are structured to produce an expected ecological pattern in the absence of a hypothesized mechanism, can serve as suitable benchmarks. Using a classic case study of mallard harvest management that is often used to demonstrate the successes of ARM for learning about ecological mechanisms, we show that simple ecological null models, such as population persistence (Nt +1 = Nt ), provide more robust near-term forecasts of population abundance than the currently used mechanistic models. More broadly, ecological null models can be used as benchmarks for learning in ARM that trigger the need for discarding model parameterizations and developing new ones when prevailing models underperform the ecological null model. Identifying mechanistic models that surpass these benchmarks will improve learning through ARM and help decision-makers keep pace with a rapidly changing world.

Dataset Information

Frequencies of decision making and monitoring in adaptive resource management.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets