About this Research Topic
Aerosol drug delivery is widely used for the treatment of respiratory diseases, such as asthma and COPD. In these treatments, medication is delivered directly to the lungs in the form of fine aerosols, allowing for rapid and targeted therapeutic effects.
In the past decades, substantial progress has been made in the field of numerical modelling for aerosol drug delivery. With the increasing power of computers and the development of new algorithms, numerical modelling has been instrumental in the development and optimization of inhaler devices to improve the flow profiles to deagglomerate particles and increase the delivered aerosol fine particle dose.
The emerging machine learning (ML) models are increasingly being applied for process optimisation. It allows systems to learn and improve from experience without the need to define explicit relations. It has advantages in finding hidden patterns and extracting features from large data sets, rapidly making predictions and classifications with higher accuracy compared to empirical equations, and with relatively low computation cost.
While numerical modeling, such as computational fluid dynamics (CFD) and discrete element method (DEM) is a feasible and powerful tool to generate detailed information to facilitate a better understanding of the underlying mechanisms of aerosol drug delivery, challenges remain when applying numerical modeling to complex aerosol drug delivery systems. One challenge is the validation of these models through experimental data, as the complex nature of multiphase flow in inhaler devices and the respiratory system makes it difficult to obtain comprehensive measurements. Another challenge is the extremely high computational cost of performing high-fidelity simulations.
On the other hand, ML describes the relationships between inputs and outputs using machine learning and big data. The effectiveness of ML models relies heavily on the breadth and quality of the data, and the rules for deep learning. The lack of interpretability and explainability based on underlying physics has been a bottleneck for the application of ML to aerosol drug delivery.
The main goal of the Research Topic is thus to present the recent applications of numerical modelling and ML technologies to aerosol drug delivery. In addition, the collection aims to identify key areas in aerosol drug delivery in which numerical modelling and ML can be integrated to provide improved accuracy and effectiveness in drug formulation and device designs as well as patient-specific treatments.
The scope of this Research Topic encompasses a range of topics related to the recent advances in numerical and ML modelling of aerosol drug delivery systems, including but not limited to drug formulation, aerosol generation, and inhaler design, aerosol transport in the respiratory tract, dosage optimization, real-time feedback and control and adaptive treatment plans.
We welcome authors to submit original research papers, review articles, and case studies that shed light on the innovative methodologies and applications in this field.
Specific themes include:
• Development of numerical modeling techniques in simulating multiphase flow
• Development ML algorithms in aerosol drug delivery
• Applications of numerical and ML models in improving aerosol drug delivery efficiency.
• Integration of numerical modeling and ML in simulating aerosol drug delivery.
• Experimental data for the validation and training of models.
In the past decades, substantial progress has been made in the field of numerical modelling for aerosol drug delivery. With the increasing power of computers and the development of new algorithms, numerical modelling has been instrumental in the development and optimization of inhaler devices to improve the flow profiles to deagglomerate particles and increase the delivered aerosol fine particle dose.
The emerging machine learning (ML) models are increasingly being applied for process optimisation. It allows systems to learn and improve from experience without the need to define explicit relations. It has advantages in finding hidden patterns and extracting features from large data sets, rapidly making predictions and classifications with higher accuracy compared to empirical equations, and with relatively low computation cost.
While numerical modeling, such as computational fluid dynamics (CFD) and discrete element method (DEM) is a feasible and powerful tool to generate detailed information to facilitate a better understanding of the underlying mechanisms of aerosol drug delivery, challenges remain when applying numerical modeling to complex aerosol drug delivery systems. One challenge is the validation of these models through experimental data, as the complex nature of multiphase flow in inhaler devices and the respiratory system makes it difficult to obtain comprehensive measurements. Another challenge is the extremely high computational cost of performing high-fidelity simulations.
On the other hand, ML describes the relationships between inputs and outputs using machine learning and big data. The effectiveness of ML models relies heavily on the breadth and quality of the data, and the rules for deep learning. The lack of interpretability and explainability based on underlying physics has been a bottleneck for the application of ML to aerosol drug delivery.
The main goal of the Research Topic is thus to present the recent applications of numerical modelling and ML technologies to aerosol drug delivery. In addition, the collection aims to identify key areas in aerosol drug delivery in which numerical modelling and ML can be integrated to provide improved accuracy and effectiveness in drug formulation and device designs as well as patient-specific treatments.
The scope of this Research Topic encompasses a range of topics related to the recent advances in numerical and ML modelling of aerosol drug delivery systems, including but not limited to drug formulation, aerosol generation, and inhaler design, aerosol transport in the respiratory tract, dosage optimization, real-time feedback and control and adaptive treatment plans.
We welcome authors to submit original research papers, review articles, and case studies that shed light on the innovative methodologies and applications in this field.
Specific themes include:
• Development of numerical modeling techniques in simulating multiphase flow
• Development ML algorithms in aerosol drug delivery
• Applications of numerical and ML models in improving aerosol drug delivery efficiency.
• Integration of numerical modeling and ML in simulating aerosol drug delivery.
• Experimental data for the validation and training of models.
Keywords: aerosol drug delivery, dry powder inhaler, computational fluid dynamics, discrete element method, machine learning, numerical modeling, data-drive models
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
