Journal of Korean biological nursing science · 2025
Artificial intelligence in emergency department triage: a scoping review on workload reduction and patient safety enhancement.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Kim Seoyoung, Nam Soo-Hyun, Lee Jungmin
Аннотация
PURPOSE: This scoping review aimed to evaluate current evidence regarding the application of artificial intelligence (AI)-based triage systems in emergency departments (EDs), with a focus on their contributions to workload reduction, patient safety, and decision-making accuracy from a nursing perspective.
METHODS: A scoping review was conducted in accordance with PRISMA-ScR guidelines. Six electronic databases (PubMed, CINAHL Plus with Full Text, JSTOR, IEEE Xplore, ProQuest, and Web of Science) were searched for articles published between January 2014 and December 2024. Studies were included if they applied AI techniques to ED triage and reported outcomes related to workload, safety, or triage performance. Data were extracted and thematically analyzed to identify key contributions of AI-based triage systems. Eight studies met the inclusion criteria.
RESULTS: Three major themes were identified: (1) improvement in decision-making accuracy through AI-assisted triage models, (2) reduction in clinician workload, and (3) enhanced identification of critically ill patients contributing to patient safety. Some models achieved high predictive performance, with Area Under the Receiver Operating Characteristic Curve scores reaching up to 0.96. However, heterogeneity in study designs and limited nurse involvement restricted the generalizability and clinical applicability of these studies.
CONCLUSION: This review synthesizes existing literature on AI-supported triage systems in emergency care and provides foundational insights into their potential to support nursing decision-making. Future research should focus on nurse-centered system design, usability testing in real-world settings, and evaluation of clinical outcomes to ensure effective and ethical integration into nursing practice.
METHODS: A scoping review was conducted in accordance with PRISMA-ScR guidelines. Six electronic databases (PubMed, CINAHL Plus with Full Text, JSTOR, IEEE Xplore, ProQuest, and Web of Science) were searched for articles published between January 2014 and December 2024. Studies were included if they applied AI techniques to ED triage and reported outcomes related to workload, safety, or triage performance. Data were extracted and thematically analyzed to identify key contributions of AI-based triage systems. Eight studies met the inclusion criteria.
RESULTS: Three major themes were identified: (1) improvement in decision-making accuracy through AI-assisted triage models, (2) reduction in clinician workload, and (3) enhanced identification of critically ill patients contributing to patient safety. Some models achieved high predictive performance, with Area Under the Receiver Operating Characteristic Curve scores reaching up to 0.96. However, heterogeneity in study designs and limited nurse involvement restricted the generalizability and clinical applicability of these studies.
CONCLUSION: This review synthesizes existing literature on AI-supported triage systems in emergency care and provides foundational insights into their potential to support nursing decision-making. Future research should focus on nurse-centered system design, usability testing in real-world settings, and evaluation of clinical outcomes to ensure effective and ethical integration into nursing practice.