Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

High-throughput identification of bacterial β-glucuronidase inhibitors using machine learning.

Gut microbes·2026
Same author

Melatonin-loaded 3D-printed carboxymethyl cellulose-gold nanoparticles composite hydrogels for wound healing.

International journal of biological macromolecules·2026
Same author

Microbubbles manufactured using a tissue homogeniser: DoE-guided optimisation for a narrower size distribution and higher yield.

International journal of pharmaceutics·2026
Same author

Artificial intelligence-enabled personalisation of oral drug delivery: From data-driven design to on-demand manufacturing.

Advanced drug delivery reviews·2026
Same author

A multi-strain probiotic modulates gut microbiome composition, intestinal barrier integrity and inflammation in a multi-compartmental in vitro gut model of decompensated advanced chronic liver disease.

International journal of pharmaceutics·2026
Same author

Technical pen-based printhead for high-precision microdosing of personalized therapies.

Drug delivery and translational research·2026

Related Experiment Video

Updated: Sep 6, 2025

Multimodal 3D Printing of Phantoms to Simulate Biological Tissue
05:11

Multimodal 3D Printing of Phantoms to Simulate Biological Tissue

Published on: January 11, 2020

7.6K

Accelerating 3D printing of pharmaceutical products using machine learning.

Jun Jie Ong1, Brais Muñiz Castro2, Simon Gaisford1,3

  • 1Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.

International Journal of Pharmaceutics: X
|June 27, 2022
PubMed
Summary

Machine learning models predict pharmaceutical 3D printing outcomes using a balanced dataset of hot melt extrusion and fused deposition modeling formulations. This accelerates personalized medicine development.

Keywords:
3D printed drug products and medicinesAdditive manufacturing of pharmaceuticalsArtificial intelligence and digital healthFused filament fabrication and Fused deposition modellingManufacture of medicinal productsMaterial extrusion and drug delivery systemsPrinting medical devices and implants

More Related Videos

Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications
09:08

Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications

Published on: August 30, 2018

12.5K
3D Printing of Preclinical X-ray Computed Tomographic Data Sets
11:06

3D Printing of Preclinical X-ray Computed Tomographic Data Sets

Published on: March 22, 2013

40.6K

Related Experiment Videos

Last Updated: Sep 6, 2025

Multimodal 3D Printing of Phantoms to Simulate Biological Tissue
05:11

Multimodal 3D Printing of Phantoms to Simulate Biological Tissue

Published on: January 11, 2020

7.6K
Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications
09:08

Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications

Published on: August 30, 2018

12.5K
3D Printing of Preclinical X-ray Computed Tomographic Data Sets
11:06

3D Printing of Preclinical X-ray Computed Tomographic Data Sets

Published on: March 22, 2013

40.6K

Area of Science:

  • Pharmaceutical science
  • Materials science
  • Computational chemistry

Background:

  • Three-dimensional printing (3DP) offers personalized medicine and device fabrication but faces formulation development challenges.
  • Machine learning (ML) can predict formulation outcomes, but requires balanced datasets, often lacking negative results from literature.
  • Existing ML models for pharmaceutical 3DP are limited by smaller, imbalanced datasets.

Purpose of the Study:

  • To develop optimized ML models for predicting pharmaceutical 3DP formulation outcomes.
  • To create a balanced dataset by combining in-house and literature data for HME and FDM 3DP.
  • To integrate predictive models into a user-friendly web application to streamline formulation development.

Main Methods:

  • Compiled a balanced dataset of 1594 pharmaceutical 3DP formulations from in-house and literature sources.
  • Utilized machine learning to develop predictive models for printability, filament characteristics, and processing temperatures.
  • Integrated optimized ML models into the M3DISEEN web application for accessible predictions.

Main Results:

  • ML models achieved 84% accuracy in predicting printability and filament mechanical characteristics.
  • Predicted HME and FDM processing temperatures with mean absolute errors of 5.5°C and 8.4°C, respectively.
  • Demonstrated improved performance over previous models using smaller, imbalanced datasets.

Conclusions:

  • A structured, heterogeneous dataset is crucial for optimal ML model performance in pharmaceutical 3DP.
  • The M3DISEEN web application significantly expedites the empirical formulation development process.
  • Enhanced ML predictions facilitate higher throughput in pharmaceutical 3DP research and development.