Image-based predictive modelling frameworks for personalised drug delivery in cancer therapy

Area of Science:

• Biomedical Engineering
• Pharmacology
• Computational Biology

Background:

• Conventional drug delivery uses generic strategies, potentially leading to suboptimal effectiveness and increased adverse effects.
• Individual patient differences significantly impact physiological and physicochemical processes in drug delivery.
• Understanding these patient-specific factors is critical for optimizing treatment outcomes.

Purpose of the Study:

• To provide an overview of multiphysics models for personalised drug delivery.
• To discuss the integration of these models with advanced medical imaging.
• To explore the potential of new technologies like machine learning in this field.

Main Methods:

• Review of existing multiphysics modelling frameworks for drug delivery.
• Analysis of model integration with medical imaging modalities.
• Discussion of computational code packages and emerging technologies.

Main Results:

• Multiphysics models offer a feasible approach to study individual effects on drug delivery in patient-specific environments.
• Extensive modelling frameworks exist to elucidate drug delivery mechanisms and optimize treatment plans.
• Integration with medical imaging and potential incorporation of machine learning enhance model capabilities.

Conclusions:

• Multiphysics models are essential for advancing personalised drug delivery by accounting for patient-specific variations.
• The combination of modelling, advanced imaging, and machine learning holds significant promise for future drug delivery optimization.
• This approach facilitates precise treatment, improves drug effectiveness, and enhances patient quality of life.