Introduction: Artificial intelligence (AI) has rapidly emerged as a transformative tool in anesthesiology, offering innovative solutions to enhance clinical decision-making, procedural accuracy, and patient safety. The field, which relies heavily on real-time interpretation of complex physiological data, stands to benefit significantly from AI-powered tools, particularly in ultrasound-guided regional anesthesia (UGRA), depth-of-anesthesia (DoA) monitoring, and prediction of perioperative complications. Methodology: A systematic review was conducted in accordance with preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines, analyzing literature from January 1, 2015, to June 30, 2025. PubMed and Google Scholar were searched, yielding 518 records. After exclusions, 5 high-quality studies were selected based on SANRA scoring. Results: Studies demonstrated the utility of AI in various domains. ScanNav-assisted UGRA improved anatomical identification and training confidence. Artificial neural networks (ANNs) outperformed traditional monitors in classifying DoA states. Machine learning (ML) models accurately predicted postoperative sore throat and postinduction hypotension using multi-parametric clinical and echocardiographic data. Automated neuraxial ultrasound systems showed 79.1% first-pass success for spinal anesthesia, especially in obese patients. Conclusion: AI enhances anesthetic practice by improving accuracy, personalization, and training outcomes. Despite challenges like interpretability and generalizability, AI-integrated tools show great promise in advancing perioperative care. Continued validation, ethical oversight, and workflow integration are essential for safe and effective implementation.
BV et al. (Thu,) studied this question.