This review explores the pivotal role of cardiopulmonary resuscitation (CPR) in the chain of survival during cardiac events and delves into the challenges and advancements in CPR techniques and technologies. While manual interventions and automated devices have improved survival rates, they present limitations such as rescuer fatigue and lack of real-time feedback. The emergence of the Internet of Medical Things (IoMT) and machine learning (ML) algorithms offers transformative opportunities to enhance CPR rescue efforts by facilitating real-time data acquisition, remote monitoring, and adaptive feedback. However, challenges including interoperability and data security must be addressed for effective integration. The study discusses major findings from related literature, gaps in research, and future directions, highlighting the potential of integrating IoMT and ML to improve CPR outcomes and revolutionize healthcare delivery. Finally, it concludes with recommendations for optimizing CPR strategies and advancing technology for better patient outcomes.

Cardiopulmonary Resuscitation CPR IoMT Real-Time Adaptive Feedback Machine Learning Healthcare Integration