Classification of Pharmaceutical Solid Excipients Using Self-Organizing Maps

In pharmaceutical technology the study of rheological behavior of powders is an important step in pre formulation of solid dosage forms. These studies, particularly the flow behavior of powders, is an exhausting and very time consuming task, which requires tools that render this process faster while maintaining accuracy. The self-organizing map (SOM) is tool in the exploratory phase of data mining. It projects data from input space to low-dimensional regular grid which may be effectively utilized to visualize and explore properties of the data. This paper applies self-organizing map and K-means in order to analyze rheological characteristics of pharmaceutical solid excipients and their binary mixtures e.q. attapulgite, a natural clay candidate to solid excipient. Self-organizing map was able to classify effectively the excipients in ordered and coherent groups and classified attapulgite as a characteristic grouping having properties far distinct from the other groups of excipients. SOM enabled a reduction of experiments via exploratory data analysis about the rheological behavior of these powders.

[1]  M. Pozo,et al.  Clay and non-clay minerals in the pharmaceutical and cosmetic industries Part II. Active ingredients , 2010 .

[2]  M. Netto,et al.  An unsupervised method of classifying remotely sensed images using Kohonen self‐organizing maps and agglomerative hierarchical clustering methods , 2008 .

[3]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Yeuvo Jphonen,et al.  Self-Organizing Maps , 1995 .

[5]  Otto Opitz,et al.  Information and Classification , 1993 .

[6]  J. L. Legido,et al.  Comparative study of the cooling rates of bentonite, sepiolite and common clays for their use in pelotherapy , 2007 .

[7]  C. Viseras,et al.  Pharmaceutical applications of some spanish clays (sepiolite, palygorskite, bentonite): some preformulation studies , 1999 .

[8]  José Alfredo Ferreira Costa,et al.  Estimating the Number of Clusters in Multivariate Data by Self-Organizing Maps , 1999, Int. J. Neural Syst..

[9]  C. Caramella,et al.  Use of clays as drug delivery systems: Possibilities and limitations , 2007 .

[10]  C. Viseras,et al.  Current challenges in clay minerals for drug delivery , 2010 .

[11]  José Alfredo Ferreira Costa.  Clustering and Visualizing SOM Results , 2010, IDEAL.

[12]  José Alfredo Ferreira Costa,et al.  Clustering of complex shaped data sets via Kohonen maps and mathematical morphology , 2001, Data Mining and Knowledge Discovery: Theory, Tools, and Technology.

[13]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[14]  A. Ultsch,et al.  Self-Organizing Neural Networks for Visualisation and Classification , 1993 .

[15]  Hujun Yin,et al.  Intelligent Data Engineering and Automated Learning - IDEAL 2010, 11th International Conference, Paisley, UK, September 1-3, 2010. Proceedings , 2010, IDEAL.

[16]  M. Pozo,et al.  Clay and non-clay minerals in the pharmaceutical industry: Part I. Excipients and medical applications , 2009 .