Current state of machine learning implementation in pharmaceutical process modeling for oral solid dosage forms.

Area of Science:

• Pharmaceutical Manufacturing
• Industrial Chemistry
• Data Science

Background:

• The pharmaceutical industry is shifting towards advanced manufacturing, driven by regulatory initiatives and Industry 4.0.
• This transition necessitates predictive modeling, real-time optimization, and quality control.

Purpose of the Study:

• To review the applications of machine learning (ML) in oral solid dosage form manufacturing.
• Focus on unit operations and Process Analytical Technology (PAT).

Main Methods:

• Review of ML applications in pharmaceutical manufacturing.
• Focus on wet granulation, extrusion, and PAT frameworks.
• Analysis of ML for critical quality attribute prediction and process parameter optimization.

Main Results:

• ML applications include predicting granule size distribution and moisture content.
• ML optimizes extrusion process parameters for desired product qualities.
• Development of adaptive, real-time PAT frameworks using ML.

Conclusions:

• ML shows significant promise for advanced pharmaceutical manufacturing requirements.
• Challenges include data availability, model interpretability, and integration.
• Future work involves digital twins, scalability, and uncertainty quantification.