Artificial Intelligence (AI)-Driven Approaches to Manage Postoperative Pain, Anxiety, and Psychological Outcomes in...

Postoperative pain, anxiety, and psychological distress significantly impact surgical recovery, yet conventional management strategies often lack personalization. Artificial intelligence (AI) has emerged as a transformative tool in perioperative care, offering potential solutions through predictive analytics, real-time monitoring, and tailored interventions. This systematic review synthesizes evidence on AI-driven approaches for improving postoperative pain, anxiety, and psychological outcomes in surgical patients. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a comprehensive search of PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, Scopus, Web of Science, and Cochrane Library up to April 2025. Ten studies met the inclusion criteria. Risk of bias was assessed using the revised Cochrane risk of bias tool for randomized trials (ROB 2) and Risk Of Bias In Non-randomized Studies-of Interventions (ROBINS-I) for non-randomized studies. Data were narratively synthesized by AI applications (e.g., nociception monitoring, robotics, machine learning (ML)) and outcomes (pain, anxiety, psychological metrics). AI interventions demonstrated efficacy in reducing postoperative pain (e.g., nociception level (NOL)-guided analgesia lowered pain scores by 33% vs. standard care) and anxiety (e.g., interactive robots reduced pediatric preoperative anxiety). ML models predicted pain severity (area under the curve (AUC) up to 0.75) and complications (AUC 0.84) but showed lower accuracy for readmissions (AUC 0.66). Automated psychological interventions reduced opioid use by 36.5%. Limitations included small sample sizes (12 to 201 participants), heterogeneity in AI methods, and short follow-up durations. AI shows promise in personalizing perioperative care, particularly for pain and anxiety management, though standardization and larger trials are needed. Future research should prioritize robust validation, long-term outcomes, and integration into clinical workflows to translate AI's potential into routine practice.