Related Experiment Video
Updated: Oct 26, 2025
09:08
Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications
Published on: August 30, 2018
12.7K
Machine learning predicts 3D printing performance of over 900 drug delivery systems
Brais Muñiz Castro1, Moe Elbadawi2, Jun Jie Ong2
1IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain.
Summary
Artificial intelligence (AI) and machine learning (ML) can accelerate pharmaceutical 3D printing (3DP) by predicting formulation properties. ML models achieved 93% accuracy in predicting 3DP processes and accurately forecast drug release, optimizing personalized medicine development.
Area of Science:
- Pharmaceutical Sciences
- Materials Science
- Computational Science
Background:
- Three-dimensional printing (3DP) offers personalized medicine but faces optimization challenges.
- Artificial intelligence (AI) can analyze large datasets to overcome these limitations.
Purpose of the Study:
- To develop and evaluate AI machine learning (ML) models for predicting 3DP pharmaceutical formulation and dissolution.
- To identify key variables influencing the 3DP process and drug release.
Main Methods:
- Literature mining of 968 formulations from 114 articles.
- Development of ML models, including artificial neural networks, to predict process parameters and in vitro drug release.
- Analysis of formulation composition and process variables.
Main Results:
- ML models achieved up to 93% accuracy in predicting filament hot melt extrusion parameters.
- An artificial neural network accurately predicted drug release times with a mean error of ±24.29 minutes.
- Key formulation and process variables influencing 3DP were identified.
Conclusions:
- Machine learning is a viable approach for modeling the 3D printing workflow in pharmaceutical development.
- AI/ML can significantly reduce trial-and-error, accelerating the optimization of 3D printed medicines.
- This approach facilitates the development of personalized drug products through efficient formulation design.
