This systematic review by Teo et al. provides a comprehensive overview of federated learning (FL) in healthcare, analyzing 612 articles. FL is a distributed machine learning framework that allows multiple parties to collaboratively train models while preserving data privacy. The review highlights that only 5.2% of the studies included real-life applications of FL, with radiology and internal medicine being the most common specialties using FL. FL is compatible with various data types and machine learning models, particularly neural networks and medical imaging. The review identifies key barriers to clinical translation, including privacy breaches, data quality issues, explainability challenges, infrastructure requirements, and intellectual property considerations. Future research should focus on addressing these barriers to enhance the clinical adoption of FL, making it a pivotal strategy for global health collaboration.This systematic review by Teo et al. provides a comprehensive overview of federated learning (FL) in healthcare, analyzing 612 articles. FL is a distributed machine learning framework that allows multiple parties to collaboratively train models while preserving data privacy. The review highlights that only 5.2% of the studies included real-life applications of FL, with radiology and internal medicine being the most common specialties using FL. FL is compatible with various data types and machine learning models, particularly neural networks and medical imaging. The review identifies key barriers to clinical translation, including privacy breaches, data quality issues, explainability challenges, infrastructure requirements, and intellectual property considerations. Future research should focus on addressing these barriers to enhance the clinical adoption of FL, making it a pivotal strategy for global health collaboration.