Related Experiment Video
Updated: Jun 8, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
Self-organizing map analysis using multivariate data from theophylline powders predicted by a thin-plate spline
Akihito Yasuda1, Yoshinori Onuki, Shingo Kikuchi
1Department of Pharmaceutics, Hoshi University, 2-4-41 Ebara, Shinagawa-ku, Tokyo 142-8501, Japan.
This study integrates thin-plate spline (TPS) interpolation and Kohonen
Area of Science:
- Pharmaceutical Sciences
- Chemical Engineering
- Materials Science
Background:
- Quality by Design (QbD) is crucial for pharmaceutical formulation development, requiring a science-based rationale and defined design space.
- Understanding the complex relationships between formulation factors and drug product performance is essential for robust pharmaceutical development.
- Traditional methods may not fully capture the intricate correlations between various formulation parameters and their impact on drug properties.
Purpose of the Study:
- To integrate thin-plate spline (TPS) interpolation and Kohonen's self-organizing map (SOM) for visualizing the latent structure in pharmaceutical formulation data.
- To quantitatively predict pharmaceutical responses (e.g., powder properties) using TPS and analyze correlations between causal factors and these responses via SOM.
- To enhance the understanding of theophylline powder formulations by identifying critical formulation parameters influencing powder characteristics.
Main Methods:
- Preparation of theophylline powders using a standard formulation.
- Measurement of response variables: angle of repose, compressibility, cohesion, and dispersibility.
- Application of nonlinear thin-plate spline (TPS) interpolation for quantitative prediction of responses and Kohonen's self-organizing map (SOM) for data clustering and correlation analysis.
Main Results:
- Experimental powder properties were accurately predicted using nonlinear TPS.
- Generated powder data were successfully classified into distinctive clusters using SOM.
- SOM analysis revealed significant correlations between causal factors (e.g., microcrystalline cellulose and magnesium stearate quantities) and powder characteristics.
Conclusions:
- The integrated TPS and SOM approach effectively visualizes latent structures and correlations in pharmaceutical formulation data.
- This methodology provides a powerful tool for understanding the impact of critical formulation parameters on drug product performance.
- The study demonstrates the utility of TPS-SOM for optimizing theophylline powder formulations and potentially other pharmaceutical products.
Related Concept Videos
Pharmacodynamic Models: Additive and Proportional Drug Effect Model
Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This relationship...
Analysis of Population Pharmacokinetic Data
Drug Concentration Versus Time Correlation
Two pivotal parameters are the minimum effective concentration (MEC) and the minimum toxic concentration (MTC). The MEC is the lowest drug...
Noncompartmental Analysis: Mean Transit, Absorption and Dissolution Time
One of the key parameters is the mean transit time (MTT), which refers to the total duration required for drug molecules to transit through the body. MTT is determined by calculating the ratio of the area under the moment curve to the area...
Noncompartmental Analysis: Miscellaneous Pharmacokinetic Parameters
One key aspect of the noncompartmental approach is determining a drug's total clearance. This can be done by dividing the drug dose by the area under the concentration-time curve from zero to infinity. The area under the concentration-time curve represents the drug's overall...
