運用貝氏方法建立藥品溶解度之模型

Abstract

藥品在人體的吸收是根據藥品的溶解度，所以合適的溶解特徵對於我們確定藥品是否達到我們希望的治療效果是非常重要的，為了評定相似的溶解率，我們應用了 general growth curve model ，和不同的藥品量來分析與預測。美國國家藥物與食品管理委員會(FDA)規定任何藥品上市前，都必須作溶解度的測試，在本研究中，溶解率隨著不同的時間在測量，其中測量的時間點：1,2,3,4,6,8,10 min，我們興趣在於比較 Lee at al. (1999) 用MLE 估計與預測，和我們以貝氏觀點所做的估計與預測何者較優。

This paper proposes a growth-curve model coupled with Box-Cox transformation to model the dissolution data such as those given in Table 1. The proposed methods are based on a regression model for the dissolution rates with the time of observations as the independent variable. Bayesian estimation of parameters and prediction of future values are considered in Section 2 and Section 3 , respectively. Bayesian Inference via MCMC methodology is considered in Section 4 . Section 5 is denoted to numerical illustrations with real and simulated data .