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

Modified-Release Drug Delivery Systems: Drug Release Characteristics01:22

Modified-Release Drug Delivery Systems: Drug Release Characteristics

257
Drug release from modified-release dosage forms is designed to achieve specific therapeutic effects by controlling the rate and extent of drug release. The classification of these drug release systems is based on key pharmacokinetic assumptions: drug disposition follows first-order kinetics, drug release is the rate-limiting step in absorption, and the released drug is rapidly and completely absorbed.There are four major models of drug release patterns. The first model is the slow zero-order...
257
Modified-Release Drug Delivery Systems: Influencing Factors01:20

Modified-Release Drug Delivery Systems: Influencing Factors

208
Modified-release drug delivery systems are designed to optimize the therapeutic effect of drugs by minimizing side effects, reducing the dosage required, and controlling drug release to align with pharmacokinetic and pharmacodynamic needs. The system depends on two key factors: the drug's release from the formulation and its movement through the body to the target site. Unlike conventional dosage forms, where absorption is the limiting step, the rate of drug release is the key determinant in...
208
Modified-Release Drug Delivery Systems: Classification01:23

Modified-Release Drug Delivery Systems: Classification

315
Modified-release drug delivery systems improve drug efficacy and minimize side effects by controlling the rate and location of drug release. These systems fall into three categories: rate-programmed, stimuli-activated, and site-targeted.Rate-programmed systems release drugs at a predetermined rate, maintaining consistent therapeutic levels and reducing fluctuations that could lead to toxicity or subtherapeutic effects. These systems use polymeric matrices, reservoir-based designs, or osmotic...
315
Drug Delivery Systems: Different Types01:27

Drug Delivery Systems: Different Types

406
Conventional oral drug products, termed immediate-release (IR) formulations, are engineered to promptly release their active pharmaceutical ingredient (API) upon ingestion, typically in tablets or capsules. This rapid release often results in swift drug absorption and consequent pharmacodynamic effects, although the timing and intensity can vary depending on the drug's properties. Prodrugs within these formulations require metabolic conversion to activate their pharmacodynamic effects,...
406
Modified-Release Drug Delivery Systems: Rate-Programmed II01:19

Modified-Release Drug Delivery Systems: Rate-Programmed II

137
Rate-programmed drug delivery systems release drugs in a controlled manner to maintain therapeutic levels. Three main designs include reservoir, matrix, and hybrid systems.Reservoir systems consist of a drug core enclosed within a membrane that controls drug release. In non-swelling reservoir systems, polymers like ethyl cellulose or polymethacrylates are used. These do not hydrate in aqueous media and control release through membrane thickness, porosity, or insolubility. This type includes...
137
Modified-Release Drug Delivery Systems: Overview01:19

Modified-Release Drug Delivery Systems: Overview

236
Modified-release dosage forms are designed to address the limitations of drugs with short biological half-lives. These forms maintain stable therapeutic drug concentrations over extended periods, reducing the need for frequent dosing. A consistent drug level helps minimize peak-trough fluctuations, which can reduce adverse effects, lower the risk of drug resistance, and improve overall treatment effectiveness.One common type of modified-release form is the extended-release (ER) formulation. ER...
236

You might also read

Related Articles

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

Sort by
Same author

Predicting Early and Complete Drug Release from Long-Acting Injectables Using Explainable Machine Learning.

ArXiv·2026
Same author

Advances in Electrospun Poly(ε-caprolactone)-Based Nanofibrous Scaffolds for Tissue Engineering.

Polymers·2024
Same author

Attention-based Imputation of Missing Values in Electronic Health Records Tabular Data.

Proceedings. IEEE International Conference on Healthcare Informatics·2024
Same author

Deep Clustering of Electronic Health Records Tabular Data for Clinical Interpretation.

... IEEE International Conference on Telecommunications and Photonics. IEEE International Conference on Telecommunications and Photonics·2024
Same author

Deep imputation of missing values in time series health data: A review with benchmarking.

Journal of biomedical informatics·2023
Same author

Perturbation of deep autoencoder weights for model compression and classification of tabular data.

Neural networks : the official journal of the International Neural Network Society·2022
Same journal

A "three-in-one" nose-to-brain delivery strategy: intranasal vancomycin spray achieves simultaneous clearance of pneumococcal colonization, bacteremia, and meningitis.

International journal of pharmaceutics·2026
Same journal

10-Hydroxy-2-decenoic acid /matrine deep eutectic solvent encapsulated in hyalurosomes for enhanced transdermal delivery and antioxidant efficacy.

International journal of pharmaceutics·2026
Same journal

Dual-trigger hyaluronic acid nanoprodrug incorporating a 2-nitrobenzenesulfonyl linker for CD44-targeted and glutathione-responsive drug delivery.

International journal of pharmaceutics·2026
Same journal

Polymeric mixed micellar nanogel enhances dermal delivery and therapeutic efficacy of tofacitinib citrate.

International journal of pharmaceutics·2026
Same journal

Localized gold nanoparticles-mediated photothermal therapy for head and neck cancer: in vivo proof-of-concept.

International journal of pharmaceutics·2026
Same journal

Design and evaluation of a pump-free ultrasonic atomization-driven hollow microneedle array for transdermal drug delivery.

International journal of pharmaceutics·2026
See all related articles

Related Experiment Video

Updated: May 3, 2026

Preparation and Characterization of Individual and Multi-drug Loaded Physically Entrapped Polymeric Micelles
07:32

Preparation and Characterization of Individual and Multi-drug Loaded Physically Entrapped Polymeric Micelles

Published on: August 28, 2015

11.0K

Predicting early and complete drug release from long-acting injectables using explainable machine learning.

Karla N Robles1, Manar D Samad2

  • 1TIGER Institute, Tennessee State University, Nashville, TN 37209, United States.

International Journal of Pharmaceutics
|May 1, 2026
PubMed
Summary
This summary is machine-generated.

Machine learning models predict drug release from long-acting injectables (LAIs) by analyzing material properties, not just time. This approach optimizes LAI development for chronic disease treatments.

Keywords:
Drug deliveryDrug releaseLong-acting injectablesMachine learningMicroparticlesPolymers

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.0K

Related Experiment Videos

Last Updated: May 3, 2026

Preparation and Characterization of Individual and Multi-drug Loaded Physically Entrapped Polymeric Micelles
07:32

Preparation and Characterization of Individual and Multi-drug Loaded Physically Entrapped Polymeric Micelles

Published on: August 28, 2015

11.0K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.0K

Area of Science:

  • Pharmaceutical Sciences
  • Materials Science
  • Computational Biology

Background:

  • Polymer-based long-acting injectables (LAIs) offer controlled drug delivery for chronic diseases, reducing dosing frequency.
  • Optimizing LAI physicochemical properties for controlled release is complex and time-consuming.
  • Existing machine learning (ML) models often use time as a primary feature, masking the impact of material characteristics on drug release.

Purpose of the Study:

  • To develop a novel, explainable ML approach for LAI development.
  • To predict early and complete drug release profiles from LAI formulations.
  • To identify key material characteristics influencing drug release dynamics.

Main Methods:

  • Utilized a novel data transformation and explainable ML framework.
  • Analyzed 321 LAI formulations to predict early release (24, 48, 72h), classify release profiles, and predict complete release.
  • Employed time-independent ML models and Shapley additive explanations (SHAP).

Main Results:

  • Achieved moderate correlation (0.37) for drug release prediction at 72h.
  • Obtained an F1-score of 0.72 for classifying drug release profile types.
  • Demonstrated time-independent ML models perform comparably to time-dependent models for complete release prediction, including complex profiles.
  • SHAP analysis elucidated the influence of material properties on early and complete drug release.

Conclusions:

  • The developed ML approach provides actionable insights into LAI material characteristics and drug release.
  • This method offers a quantitative strategy for optimizing LAI drug release dynamics.
  • The findings advance understanding beyond traditional time-dependent ML and in-vitro studies.