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

Factors Influencing Drug Absorption: Pharmaceutical Parameters01:28

Factors Influencing Drug Absorption: Pharmaceutical Parameters

141
Solid dosage forms such as tablets and capsules undergo rigorous manufacturing processes to ensure stability and effectiveness. Their dissolution and absorption properties are influenced significantly by the choice of excipients (inactive ingredients that serve various roles in the formulation), and the methodology applied during production. The manufacturing parameters, such as compression force and granulation techniques, significantly affect dissolution rates. Elevated compression forces...
141

You might also read

Related Articles

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

Sort by
Same author

Microstructure-centric ultrasonic evaluation of granular composite oral solid dosage tablets.

International journal of pharmaceutics·2026
Same author

COXFA4L2 upregulation preserves residual cytochrome c oxidase activity in COXFA4-related Leigh-like encephalopathy.

Nature communications·2026
Same author

Author Correction: Biallelic variants in the noncoding RNA gene RNU4-2 cause a recessive neurodevelopmental syndrome with distinct white matter changes.

Nature genetics·2026
Same author

A review of the State-of-the-Art: progress in ultrasonic and acoustic techniques for quality assessment in the development and manufacturing of oral solid dosage forms - Part II: Applications and emerging directions.

International journal of pharmaceutics·2026
Same author

The modified compressibility-based compactibility model for improved prediction of compaction properties of poorly compressible materials by accounting the bonding area-bonding strength interplay.

International journal of pharmaceutics·2026
Same author

Variants in the proteasome regulator PSMF1 cause a phenotypic spectrum from parkinsonism to perinatal lethality.

Nature communications·2026

Related Experiment Video

Updated: Jul 14, 2025

Quasistatic Mechanical Testing for Computer-Aided Design and Manufacturing Occlusal Veneers Cemented to Milled Dentin Analog Material
07:42

Quasistatic Mechanical Testing for Computer-Aided Design and Manufacturing Occlusal Veneers Cemented to Milled Dentin Analog Material

Published on: December 20, 2024

417

Machine learning framework for extracting micro-viscoelastic and micro-structural properties of compressed oral solid

Tipu Sultan1, Enamul Hasan Rozin1, Shubhajit Paul2

  • 1Department of Mechanical and Aerospace Engineering, Photo-Acoustics Research Laboratory, Clarkson University, Potsdam, NY 13699-5725, USA.

International Journal of Pharmaceutics
|October 5, 2023
PubMed
Summary

This study introduces a novel Machine Learning approach to extract micro-viscoelastic and micro-structural properties of oral solid dosage forms directly from ultrasonic waveforms. This method offers a rapid, non-destructive way to assess critical quality attributes for pharmaceutical manufacturing.

Keywords:
Compressed oral solid dosage (OSD) formsContinuous manufacturing (CM)Machine learning (ML)Micro-structure characterizationMicro-visco-elasticityMulti-output regression (MOR)Neural networks (NN)Quality by Design (QbD)Real-time release (RTR) testingUltrasonic non-destructive evaluation and testing (NDE/NDT)Ultrasonic wave dispersion

More Related Videos

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

776
Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing
09:39

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Published on: June 28, 2024

954

Related Experiment Videos

Last Updated: Jul 14, 2025

Quasistatic Mechanical Testing for Computer-Aided Design and Manufacturing Occlusal Veneers Cemented to Milled Dentin Analog Material
07:42

Quasistatic Mechanical Testing for Computer-Aided Design and Manufacturing Occlusal Veneers Cemented to Milled Dentin Analog Material

Published on: December 20, 2024

417
Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

776
Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing
09:39

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Published on: June 28, 2024

954

Area of Science:

  • Materials Science
  • Pharmaceutical Technology
  • Applied Physics
  • Machine Learning

Background:

  • Oral solid dosage (OSD) forms are micro-viscoelastic composites whose critical quality attributes depend on micro-scale properties.
  • Ultrasonic evaluation offers a non-destructive, rapid method for OSD analysis, but extracting micro-properties from waveforms is challenging.
  • Accurate characterization of OSD micro-properties is crucial for ensuring product quality, including disintegration, drug release, and structural strength.

Purpose of the Study:

  • To develop and demonstrate a novel Machine Learning (ML)-based technique for extracting micro-viscoelastic and scattering properties from ultrasonic waveforms of OSDs.
  • To address the inverse problem of determining OSD micro-properties directly from experimental ultrasonic responses.
  • To validate the ML model's effectiveness using both synthetic and physical OSD tablet data.

Main Methods:

  • Development of Multi-Output Regression models and Neural Networks for waveform analysis.
  • Generation of synthetic ultrasonic waveforms with known micro-properties for training and validation of ML models.
  • Experimental acquisition of ultrasonic waveforms from physical OSD tablets for testing the ML models.

Main Results:

  • The developed ML models successfully extracted micro-viscoelastic and micro-structural properties from synthetic OSD waveforms.
  • The ML-based technique demonstrated effectiveness in recovering specified micro-scale properties for virtual tablets.
  • Validation with physical OSD tablets showed consistency between ML-derived properties and known material characteristics.

Conclusions:

  • A novel ML-based approach enables direct extraction of OSD micro-properties from ultrasonic waveforms, overcoming inverse problem challenges.
  • This technique provides a powerful, non-destructive tool for process control and quality assessment in pharmaceutical manufacturing.
  • The study confirms the potential of ML in advancing the characterization of complex pharmaceutical materials.