Drug Release Modeling using Physics-Informed Neural Networks

2026-02-10

AI Summary

This study addresses the limitations of traditional drug release models, which rely on oversimplified assumptions and struggle to accurately predict long-term release behavior in complex geometries. To overcome this, the authors propose physics-informed neural networks (PINNs) and Bayesian PINNs (BPINNs) that integrate Fick’s second law with experimental data, uniquely combining physical constraints with Bayesian uncertainty quantification for modeling drug release from films of varying morphologies. Using only short-term data spanning 6% of the total release duration, the approach achieves up to a 40% reduction in average prediction error compared to classical models across flat, wrinkled, and crumpled films, with root-mean-square errors below 0.05. Moreover, BPINN provides reliable uncertainty estimates under noisy conditions, significantly enhancing prediction accuracy, computational efficiency, and robustness.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Accurate modeling of drug release is essential for designing and developing controlled-release systems. Classical models (Fick, Higuchi, Peppas) rely on simplifying assumptions that limit their accuracy in complex geometries and release mechanisms. Here, we propose a novel approach using Physics-Informed Neural Networks (PINNs) and Bayesian PINNs (BPINNs) for predicting release from planar, 1D-wrinkled, and 2D-crumpled films. This approach uniquely integrates Fick's diffusion law with limited experimental data to enable accurate long-term predictions from short-term measurements, and is systematically benchmarked against classical drug release models. We embedded Fick's second law into PINN as loss with 10,000 Latin-hypercube collocation points and utilized previously published experimental datasets to assess drug release performance through mean absolute error (MAE) and root mean square error (RMSE), considering noisy conditions and limited-data scenarios. Our approach reduced mean error by up to 40% relative to classical baselines across all film types. The PINN formulation achieved RMSE<0.05 utilizing only the first 6% of the release time data (reducing 94% of release time required for the experiments) for the planar film. For wrinkled and crumpled films, the PINN reached RMSE<0.05 in 33% of the release time data. BPINNs provide tighter and more reliable uncertainty quantification under noise. By combining physical laws with experimental data, the proposed framework yields highly accurate long-term release predictions from short-term measurements, offering a practical route for accelerated characterization and more efficient early-stage drug release system formulation.

Problem

• drug release modeling
• controlled-release systems
• complex geometries
• long-term prediction
• limited experimental data

Innovation

• Physics-Informed Neural Networks
• Drug Release Modeling
• Bayesian PINNs
• Fick's Law
• Accelerated Prediction