Real-time machine learning-assisted sepsis alert enhances the timeliness of antibiotic administration and diagnostic accuracy in emergency department patients with sepsis: a cluster-randomized trial

Mapping artificial intelligence models in emergency medicine: A scoping review on artificial intelligence performance in emergency care and education

Artificial intelligence (AI) is increasingly improving the processes such as emergency patient care and emergency medicine education. This scoping review aims to map the use and performance of AI models in emergency medicine regarding AI concepts. The findings show that AI-based medical imaging systems provide disease detection with 85%-90% accuracy in imaging techniques such as X-ray and computed tomography scans. In addition, AI-supported triage systems were found to be successful in correctly classifying low- and high-urgency patients. In education, large language models have provided high accuracy rates in evaluating emergency medicine exams. However, there are still challenges in the integration of AI into clinical workflows and model generalization capacity. These findings demonstrate the potential of updated AI models, but larger-scale studies are still needed.

Artificial Intelligence in Sepsis Management: An Overview for Clinicians

Sepsis is one of the leading causes of mortality in hospital settings, and early diagnosis is a crucial challenge to improve clinical outcomes. Artificial intelligence (AI) is emerging as a valuable resource to address this challenge, with numerous investigations exploring its application to predict and diagnose sepsis early, as well as personalizing its treatment. Machine learning (ML) models are able to use clinical data collected from hospital Electronic Health Records or continuous monitoring to predict patients at risk of sepsis hours before the onset of symptoms. Background/Objectives: Over the past few decades, ML and other AI tools have been explored extensively in sepsis, with models developed for the early detection, diagnosis, prognosis, and even real-time management of treatment strategies. Methods: This review was conducted according to the SPIDER (Sample, Phenomenon of Interest, Design, Evaluation, Research Type) framework to define the study methodology. A critical overview of each paper was conducted by three different reviewers, selecting those that provided original and comprehensive data relevant to the specific topic of the review and contributed significantly to the conceptual or practical framework discussed, without dwelling on technical aspects of the models used. Results: A total of 194 articles were found; 28 were selected. Articles were categorized and analyzed based on their focus-early prediction, diagnosis, mortality or improvement in the treatment of sepsis. The scientific literature presents mixed outcomes; while some studies demonstrate improvements in mortality rates and clinical management, others highlight challenges, such as a high incidence of false positives and the lack of external validation. This review is designed for clinicians and healthcare professionals, and aims to provide an overview of the application of AI in sepsis management, reviewing the main studies and methodologies used to assess its effectiveness, limitations, and future potential.