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

► Model the dosage decisions in COH treatment as a stochastic optimization problem. ► Design efficient approximate dynamic programming (ADP) solution algorithms. ► Compare ADP policies with the Markov decision processes (MDP) benchmark. ► Apply cutting-edge OR in evidence-based and data-driven clini...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:European journal of operational research Jg. 222; H. 2; S. 328 - 340
Hauptverfasser: He, Miao, Zhao, Lei, Powell, Warren B.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 16.10.2012
Elsevier
Elsevier Sequoia S.A
Schlagworte:
Algorithms
Applied sciences
Approximate dynamic programming
Approximation
Biological and medical sciences
Controlled ovarian hyperstimulation
Decision theory. Utility theory
Decisions
Dosage
Dynamic programming
Endocrinopathies
Exact sciences and technology
Hypothalamus. Hypophysis. Epiphysis (diseases)
Markov analysis
Markov processes
Mathematical analysis
Mathematical programming
Mathematics
Medical sciences
Medical treatment
Monitors
Non tumoral diseases. Target tissue resistance. Benign neoplasms
Operational research and scientific management
Operational research. Management science
Optimization
Optimization algorithms
OR in health services
Ovarian hyperstimulation syndrome
Ovaries
Probability and statistics
Probability theory and stochastic processes
Sciences and techniques of general use
Studies
Approximate dynamic programming
Ovarian hyperstimulation syndrome
Controlled ovarian hyperstimulation
OR in health services
Dimensionality
Markov decision
Probabilistic approach
Optimal algorithm
Hospital management
Gonadotropin
Approximation algorithm
Experimental study
Stochastic programming
Assay
Pregnancy
Optimal decision
Linear approximation
Physiology
Dynamic programming
Piecewise linearization
Piecewise-linear techniques
ISSN:0377-2217, 1872-6860
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:► Model the dosage decisions in COH treatment as a stochastic optimization problem. ► Design efficient approximate dynamic programming (ADP) solution algorithms. ► Compare ADP policies with the Markov decision processes (MDP) benchmark. ► Apply cutting-edge OR in evidence-based and data-driven clinical decision making. 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.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0377-2217
1872-6860
DOI:10.1016/j.ejor.2012.03.049