Background: Emergency Departments (EDs) are critical in providing immediate care, often under pressure from overcrowding, resource constraints, and variability in patient prioritization. Traditional triage systems, while structured, rely on subjective assessments, which can lack consistency during peak hours or mass casualty events. AI-driven triage systems present a promising solution, automating patient prioritization by analyzing real-time data, such as vital signs, medical history, and presenting symptoms. This narrative review examines the key components, benefits, limitations, and future directions of AI-driven triage systems in EDs.
Method: This narrative review analyzed peer-reviewed articles published between 2015 and 2024, identified through searches in PubMed, Scopus, IEEE Xplore, and Google Scholar. Findings were synthesized to provide a comprehensive overview of their potential and limitations.
Results: The review identifies substantial benefits of AI-driven triage, including improved patient prioritization, reduced wait times, and optimized resource allocation. However, challenges such as data quality issues, algorithmic bias, clinician trust, and ethical concerns are significant barriers to widespread adoption. Future directions emphasize the need for algorithm refinement, integration with wearable technology, clinician education, and ethical framework development to address these challenges and ensure equitable implementation.
Conclusion: AI-driven triage systems have the potential to transform ED operations by enhancing efficiency, improving patient outcomes, and supporting healthcare professionals in high-pressure environments. As healthcare demands continue to grow, these systems represent a vital innovation for advancing emergency care and addressing longstanding challenges in triage.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ijmedinf.2025.105838 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Non-Contrast Computed Tomography-Based Triage and Notification for Large Vessel Occlusion Stroke: A Before and After Study Utilizing Artificial Intelligence on Treatment Times and Outcomes.
J Clin Med
February 2025
Department of Emergency Medicine, Gil Medical Center, Gachon University College of Medicine, Incheon 21565, Republic of Korea.
: The clinical impact of automated large vessel occlusion (LVO) detection tools using non-contrast CT (NCCT) is still unknown. We evaluated whether the implementation of Heuron ELVO, an artificial intelligence (AI)-driven software for triage and notification of LVO stroke using NCCT, can reduce treatment times and improve clinical outcomes in a real-world setting. : We compared patients with LVO stroke before (pre-AI cohort, 84 patients) and after (post-AI cohort, 48 patients) the implementation of Heuron ELVO at a comprehensive stroke center.
View Article and Find Full Text PDFAI-driven triage in emergency departments: A review of benefits, challenges, and future directions.
Int J Med Inform
May 2025
Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom; Department of Public Health, York St John University, London, United Kingdom; School of Health and Care Management, Arden University, Arden House, Middlemarch Park, Coventry CV3 4FJ, United Kingdom; Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London, United Kingdom. Electronic address:
Background: Emergency Departments (EDs) are critical in providing immediate care, often under pressure from overcrowding, resource constraints, and variability in patient prioritization. Traditional triage systems, while structured, rely on subjective assessments, which can lack consistency during peak hours or mass casualty events. AI-driven triage systems present a promising solution, automating patient prioritization by analyzing real-time data, such as vital signs, medical history, and presenting symptoms.
View Article and Find Full Text PDFInternational multicenter validation of AI-driven ultrasound detection of ovarian cancer.
Nat Med
January 2025
Department of Clinical Science and Education, Södersjukhuset, Karolinska Institutet, Stockholm, Sweden.
Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking.
View Article and Find Full Text PDFAdvancements in Clinical Evaluation and Regulatory Frameworks for AI-Driven Software as a Medical Device (SaMD).
IEEE Open J Eng Med Biol
October 2024
Owing to the rapid progress in artificial intelligence (AI) and the widespread use of generative learning, the problem of sparse data has been solved effectively in various research fields. The application of AI technologies has resulted in important transformations in healthcare, particularly in radiology. To ensure the high quality, safety, and effectiveness of AI and machine learning (ML) medical devices, the US Food and Drug Administration (FDA) has established regulatory guidelines to support the performance evaluation of medical devices.
View Article and Find Full Text PDFLarge language model triaging of simulated nephrology patient inbox messages.
Front Artif Intell
September 2024
Department of Nephrology and Hypertension, Mayo Clinic, Rochester, MN, United States.
Article Synopsis
- The study assesses ChatGPT's ability to categorize nephrology patient messages as non-urgent, urgent, or emergent, crucial for timely medical care.
- In trials involving 150 simulated messages, ChatGPT showed high accuracy, correctly triaging 93% of messages in both attempts, with slight variations in overestimations and underestimations.
- The findings suggest that AI, like ChatGPT-4, could effectively improve patient communication triage in outpatient settings, enhancing operational efficiency and care quality.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!