The role of artificial intelligence in enhancing triage decisions in healthcare settings: A systematic review

Triage is an essential function of healthcare providers in various healthcare settings, such as physicians and nurses, allowing the prioritization of patients based on severity of presenting problem. Artificial intelligence (AI) provides a promising solution by enhancing the accuracy, efficiency, and consistency of triage decisions process. Although AI shows potential in supporting healthcare providers and improving patient outcomes, its role in triage is still developing and requires more research into its effectiveness, challenges, and ethical considerations.

This systematic review aims to explore the role of AI in enhancing healthcare providers triage decisions process in the various healthcare settings.

We conducted JBI Systematic Reviews and reported results following PRISMA guidelines to screen 211 studies published between January 2020 and May 2025 from databases including Google Scholar, Wiley Online Library, PsycINFO, CINAHL Plus, and Medline.

Twenty-two studies met inclusion criteria. Results indicated that AI-based triage systems outperformed traditional methods in diagnostic accuracy, efficiency, and decision support, especially for critical conditions. Additionally, the studies demonstrated statistically significant improvements over clinician-assigned Emergency Severity Index (ESI) scores. AI models used included machine learning, deep learning, natural language processing, and hybrid approaches.

AI-based triage systems present a transformative opportunity for enhancing emergency care delivery, with evidence supporting improvements in diagnostic accuracy, triage efficiency, and decision support. Successful implementation depends not only on technical performance but also on trust, usability, ethical governance, and contextual adaptation. A multidisciplinary approach will be required to fully utilize AI in numerous healthcare settings, including triage.