Real-time component-based particle size measurement and dissolution prediction during continuous powder feeding using...

Area of Science:

• Pharmaceutical Science
• Image Analysis
• Artificial Intelligence

Background:

• Accurate particle size distribution (PSD) is crucial for pharmaceutical product performance.
• Traditional PSD measurement methods can be time-consuming and may not reflect real-time manufacturing conditions.

Purpose of the Study:

• To develop and validate a machine vision system for component-based PSD determination in pharmaceutical powder blends.
• To assess the system's ability to perform real-time analysis and predict in vitro drug dissolution.

Main Methods:

• Utilized machine vision with AI-based image analysis to capture and analyze powder images during continuous feeding.
• Determined component-based PSD for acetylsalicylic acid (ASA) and calcium hydrogen phosphate (CHP) blends.
• Validated results against microscopy and used ASA PSD in a population balance model to predict dissolution.

Main Results:

• The machine vision system demonstrated good correlation with microscopy-based PSD measurements.
• Achieved effective real-time determination of PSD for individual components within a blend.
• Successfully predicted in vitro capsule dissolution profiles using the measured ASA PSD.

Conclusions:

• The developed system offers a novel, effective method for real-time PSD analysis in pharmaceutical blends.
• This technology can provide valuable insights for pharmaceutical quality control and product development.
• The approach facilitates prediction of drug product performance based on powder characteristics.