Artificial Intelligence in Cardiopulmonary Resuscitation: Revolutionizing Resuscitation Through Precision and Prediction – A Narrative Review

Comprehensive Summary

This narrative review examines the growing role of artificial intelligence (AI) in cardiopulmonary resuscitation (CPR) and its potential to improve survival and neurological outcomes following cardiac arrest. The authors conducted a structured literature review using PubMed, Scopus, and Web of Science, focusing on English-language studies published between 2015 and 2025 that addressed AI applications in CPR, including rhythm interpretation, quality monitoring, and post-resuscitation care. Across the reviewed literature, AI-driven systems demonstrated benefits such as improved detection of shockable rhythms, real-time feedback on chest compression quality, and enhanced early recognition of cardiac arrest through emergency call analysis and wearable technologies. Emerging innovations, including AI-guided drones for automated external defibrillator (AED) delivery and robotic CPR systems, showed feasibility and performance comparable to existing mechanical devices, though evidence of improved survival remains limited. The authors emphasize that while AI can reduce variability in CPR performance and support clinical decision-making, widespread clinical adoption is constrained by limited real-world validation, data quality concerns, and ethical and regulatory challenges.

Outcomes and Implications

This research is important because survival rates from cardiac arrest remain low, particularly in out-of-hospital settings, and CPR quality is highly dependent on timely intervention and rescuer performance. AI-assisted technologies have the potential to improve consistency in CPR delivery, enhance bystander response, and support clinicians through real-time feedback and predictive decision tools. Clinically, AI may be most impactful as an adjunct to existing resuscitation practices, particularly within emergency medical services, AED platforms, and CPR training programs. However, the authors note that most applications remain in early or experimental stages, and large-scale prospective trials are needed before routine implementation. Based on current evidence, meaningful clinical integration of AI-driven CPR tools is likely to occur gradually over the next several years, contingent on rigorous validation, clinician training, and the development of ethical and regulatory frameworks.