Approximate dynamic programming algorithms for optimal dosage decisions in controlled ovarian hyperstimulation

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.

[1]  J. Grossman,et al.  Building a Better Delivery System: A New Engineering/Health Care Partnership , 2005 .

[2]  Marinus J Eijkemans,et al.  Validation of a prediction model for the follicle-stimulating hormone response dose in women with polycystic ovary syndrome. , 2006, Fertility and sterility.

[3]  Barry L. Nelson,et al.  Autoregressive to anything: Time-series input processes for simulation , 1996, Oper. Res. Lett..

[4]  M. Aboulghar,et al.  Prediction of ovarian hyperstimulation syndrome (OHSS). Estradiol level has an important role in the prediction of OHSS. , 2003, Human reproduction.

[5]  V. Goossens,et al.  Assisted reproductive technology in Europe, 2004: results generated from European registers by ESHRE. , 2008, Human reproduction.

[6]  M Gissler,et al.  What is the most relevant standard of success in assisted reproduction?: The value of cryopreservation on cumulative pregnancy rates per single oocyte retrieval should not be forgotten. , 2004, Human reproduction.

[7]  Mika Gissler,et al.  Complications of IVF and ovulation induction. , 2005, Human reproduction.

[8]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[9]  Barry L. Nelson,et al.  Numerical Methods for Fitting and Simulating Autoregressive-to-Anything Processes , 1998, INFORMS J. Comput..

[10]  W P Collins,et al.  Total ovarian volume before human chorionic gonadotrophin administration for ovulation induction may predict the hyperstimulation syndrome. , 1995, Human reproduction.

[11]  Warren B. Powell,et al.  Approximate Dynamic Programming I: Modeling , 2011 .

[12]  Robert L. Collins,et al.  Office-Based Infertility Practice , 2002, Springer New York.

[13]  Richard S. Sutton,et al.  Dimensions of Reinforcement Learning , 1998 .

[14]  Barry L. Nelson,et al.  Modeling and generating multivariate time-series input processes using a vector autoregressive technique , 2003, TOMC.

[15]  J. Balasch,et al.  Follicular development and hormone concentrations following recombinant FSH administration for anovulation associated with polycystic ovarian syndrome: prospective, randomized comparison between low-dose step-up and modified step-down regimens. , 2001, Human reproduction.

[16]  M. Aboulghar,et al.  Ovarian hyperstimulation syndrome: classifications and critical analysis of preventive measures. , 2003, Human reproduction update.

[17]  Barry L. Nelson,et al.  Fitting Time-Series Input Processes for Simulation , 2005, Oper. Res..

[18]  Verena Schmid,et al.  Solving the dynamic ambulance relocation and dispatching problem using approximate dynamic programming , 2012, Eur. J. Oper. Res..

[19]  Serge Rozenberg,et al.  Epidemiology and prevention of ovarian hyperstimulation syndrome (OHSS): a review. , 2002, Human reproduction update.

[20]  A. Knutsson,et al.  A prospective, randomized comparison of two starting doses of recombinant FSH in combination with cetrorelix in women undergoing ovarian stimulation for IVF/ICSI. , 2001, Human reproduction.

[21]  A. C. Wentz,et al.  Evaluation of the exponential rise of serum estradiol concentrations in human menopausal gonadotropin-induced cycles. , 1983, Fertility and sterility.

[22]  Warren B. Powell,et al.  Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming , 2006, Machine Learning.

[23]  Luca Gianaroli,et al.  Assisted reproductive technology in Europe, 2003 , 2007 .

[24]  Denny Sakkas,et al.  Impact of duration and dose of gonadotrophins on IVF outcomes. , 2006, Reproductive biomedicine online.

[25]  N. Macklon,et al.  What is the most relevant standard of success in assisted reproduction? The next step to improving outcomes of IVF: consider the whole treatment. , 2004, Human reproduction.

[26]  Warren B. Powell,et al.  Optimal control of dosage decisions in controlled ovarian hyperstimulation , 2010, Ann. Oper. Res..

[27]  A. Nyboe,et al.  Assisted reproductive technology in Europe, 2000. Results generated from European registers by ESHRE The European IVF-monitoring programme (EIM)* 1 for the European Society of Human Reproduction and Embryology (ESHRE) 1 , 2004 .