Artificial Neural Networks and Deep Learning in Solid Organ Transplantation

Area of Science:

• Computer Science
• Medicine
• Biotechnology

Background:

• Artificial neural networks (ANNs) are increasingly utilized across diverse scientific fields, including medicine and natural language processing.
• Despite their widespread application, ANNs are often perceived as complex "black-box" models, posing challenges for interpretation.
• The application of ANNs in solid organ transplantation has a history dating back to the 1990s.

Purpose of the Study:

• To provide a clear overview of essential terminology related to artificial neural networks.
• To present example applications of ANNs within the field of solid organ transplantation.
• To offer guidance for researchers and clinicians interested in adopting ANN models.

Main Methods:

• Definitions and examples were compiled through comprehensive PubMed searches.
• A thorough review of established texts in machine learning and deep learning was conducted.
• Focus was placed on recent ANN applications processing non-tabular data like images and text.

Main Results:

• ANNs have evolved from processing tabular data to analyzing complex, non-tabular data types such as medical images and clinical notes.
• The study outlines key concepts and terminology to facilitate a better understanding of ANN functionalities.
• Practical examples illustrate the utility of ANNs in various aspects of solid organ transplantation.

Conclusions:

• Artificial neural networks hold significant potential to advance solid organ transplantation research and practice.
• Understanding ANN terminology and applications is crucial for leveraging their predictive power effectively.
• Contextual interpretation of ANN results is essential for reliable clinical application and future development.