MARKOV PROCESSES AND CLINICAL TRIAL DESIGN

这个子项目是许多研究子项目中利用 资源由NIH/NCRR资助的中心拨款提供。子项目和 调查员(PI)可能从NIH的另一个来源获得了主要资金， 并因此可以在其他清晰的条目中表示。列出的机构是 该中心不一定是调查人员的机构。 癌症等严重疾病的早期临床试验在权衡患者的风险和收益与社区的成本和收益，特别是要获得的科学信息的价值方面，面临着严峻的挑战。原则上，决策理论为这一问题提供了明确的理性解决方案。然而，评估将要获得的未来知识的价值涉及组合爆炸性计算。这项工作适应和评估了几种近似方法，包括一些为后期临床试验开发的相当新的技术，以及来自规划和机器人学的求解部分可观测的马尔可夫决策过程的技术。

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. Early stage clinical trials for serious diseases like cancer pose serious challenges in balancing the risks and benefits for the patient enrolled with the costs and benefits to the community, especially the value of the scientific information to be gained. In principle, decision theory provides a clear rational solution to the problem. However, evaluating the value of future knowledge to be gained involves combinatorially explosive calculations. This work adapts and evaluates several approximation methods, including some fairly recent techniques developed for later-stage clinical trials, and also techniques from planning and robotics for solving partially observable Markov decision processes