Weighted target interval stochastic control methods with global optimization and their applications in individualizing therapy
- First Online:
- 53 Downloads
Several improvements on the target interval stochastic control (TISC) method are addressed for individualizing therapy. In particular, a global optimization control strategy is implemented to obtain the optimal dosage regimen, and weighting functions are introduced to balance the drug efficacy and the risk of toxicity. Since general guidance is often lacking in the determination of a weighting function, we introduce a systematic approach, i.e., the standard reference gamble method of medical decision theory, for the determination of the weighting function. The population model for the individualization of theophylline therapy reported by D’Argenio and Katz is applied in this research. The present method of the integration of weighting functions and global optimal strategy offer an effective and safe means to balance the drug efficacy and risk of toxicity. In addition, it also achieves better accuracy than the existing TISC method which uses a local optimal strategy.
KeywordsTarget interval stochastic control Weighting function Bayesian estimation Dosage regimen Global optimization
Unable to display preview. Download preview PDF.
- 1.D’Argenio DZ and Katz D (1988). Application of stochastic control methods to the problem of individualizing intravenous theophylline therapy. Biomed Meas Inform Contr 2: 115–122 Google Scholar
- 3.Hu C (1994) Suboptimal control policies in medical drug therapy. PhD Dissertation, Stanford UniversityGoogle Scholar
- 7.Rowland M and Tozer T (1994). Clinical pharmacokinetics: concepts and applications. Williams & Wilkins, Baltimore Google Scholar
- 10.Wakefield J (1994). An expected loss approach to the design of dosage regimens via sampling-based methods. Statistics 43: 13–29 Google Scholar
- 11.Harold C Jr, Sox et al (1988) Medical decision making. Butterworths, BostonGoogle Scholar
- 12.Berger JO (1985). Statistical decision theory and Bayesian analysis. Springer-Verlag, New York Google Scholar
- 13.Parmigiani G (2002) Modeling in medical decision making. John Wiley & Sons, England, chap. 2Google Scholar
- 17.Statistics Toolbox User’s Guide for use with MATLAB. The Mathworks Inc. http://www.mathworks.comGoogle Scholar