Approximate dynamic programming algorithms for optimal dosage decisions in controlled ovarian hyperstimulation
Approximate dynamic programming algorithms for optimal dosage decisions in controlled ovarian hyperstimulation
复制标题
DOI：
10.1016/j.ejor.2012.03.049
复制
发表时间：
2012-10
期刊：
影响因子：
--
通讯作者：
M. He;Lei Zhao;Warrren B Powell
中科院分区：
文献类型：
--
作者：
M. He;Lei Zhao;Warrren B Powell
在控制性超促排卵（COH）治疗中，临床医生监测患者对促性腺激素给药的生理反应，以权衡妊娠概率和卵巢过度刺激综合征（OHSS）。我们制定的剂量控制问题的COH治疗作为一个随机动态规划和设计近似动态规划（ADP）算法，以克服众所周知的诅咒的维数在马尔可夫决策过程（MDP）。我们的数值实验表明，分段线性（PWL）近似ADP算法可以获得的政策是非常接近的MDP基准得到的显着更少的解决方案的时间。
In the controlled ovarian hyperstimulation (COH) treatment, clinicians monitor the patients’ physiological responses to gonadotropin administration to tradeoff between pregnancy probability and ovarian hyperstimulation syndrome (OHSS). We formulate the dosage control problem in the COH treatment as a stochastic dynamic program and design approximate dynamic programming (ADP) algorithms to overcome the well-known curses of dimensionality in Markov decision processes (MDP). Our numerical experiments indicate that the piecewise linear (PWL) approximation ADP algorithms can obtain policies that are very close to the one obtained by the MDP benchmark with significantly less solution time.