Health

Hospitals & Care · 38 stories · page 3 of 3

HealthBoth readings

Skyer: a novel benchmark for evaluating the effectiveness of large language models in emergency department triage

OBJECTIVES: Emergency department (ED) overcrowding causes diagnostic challenges, prolonged wait times, and impairs appropriate triage, often due to human error and fatigue. Large language models can assist ED staff in triage, improving patient care by mitigating these problems. METHODS: We designed an evaluation method (Skyer benchmark) to assess fifteen large language models, including DeepSeek-R1 (70B, 7B), ChatGPT versions (4, 4.5-preview), Gemini iterations (1.5-pro, 2.0-Pro-experimental, 2.5_03-25, 2.5_05-0…

Canadian Journal of Emergency Medicine

Both readings

Triage safety of patient-facing AI chatbots for nipple discharge: A guideline-informed assessment of red-flag recognition and patient actionability

Both readings

Seeing beyond the algorithm: artificial intelligence and the enduring role of the radiologist

Model-prefilled gain

A Nurse Hackathon: Improving Effective and Timely Nurse Handoffs Through Use of Generative Artificial Intelligence

Model-prefilled gain

Impact of Artificial Intelligence-Enhanced Insertable Cardiac Monitors on Device Clinic Workflow and Resource Utilization

BACKGROUND: Insertable cardiac monitors (ICMs) are essential for managing arrhythmias but often generate large numbers of transmissions and false alerts. Integrating artificial intelligence (AI) as part of the ICM workflow can reduce this burden. However, its impact on clinic workflow and resource utilization must be better understood. OBJECTIVES: The aim of the study was to assess the impact of AI-enhanced ICMs on clinic workflow and resource utilization. METHODS: A cross-sectional analysis was conducted using…

Both readings

Artificial Intelligence in Ischemic Stroke Lesion Segmentation: A Narrative Review of Deep Learning Methods, Clinical Utility, and Future Directions

Ischemic stroke management is time-sensitive, and lesion segmentation supports treatment selection, prognostication, and reproducible quantification. Deep learning (DL) aims to accelerate and standardize lesion delineation to augment neuroimaging workflows. We conducted a narrative review of DL-based ischemic stroke lesion segmentation studies published from 2020 to 2025. PubMed, Google Scholar, Scopus, and IEEE Xplore were searched; ~ 500 records were identified, and 40 full-text studies were included after scr…

Evidence-backed problem

ChatGPT Health performance in a structured test of triage recommendations

ChatGPT Health was launched in January 2026 as OpenAI's consumer health tool and has reached millions of users. Here we conducted a structured stress test of triage recommendations using 60 clinician-authored vignettes across 21 clinical domains under 16 factorial conditions, yielding 960 total responses. Performance followed an inverted U-shaped pattern, with the most dangerous failures concentrated at clinical extremes-nonurgent presentations (35%) and emergency conditions (48%). Among gold-standard emergencie…

Clinical Impact of Artificial Intelligence-Based Triage Systems in Emergency Departments: A Systematic Review

Emergency departments (EDs) worldwide face increasing pressure to optimize triage processes amidst rising patient volumes and resource constraints. Artificial intelligence (AI) has emerged as a potential solution to enhance triage accuracy and efficiency, yet its real-world clinical impact remains inadequately characterized. We conducted a systematic review following Preferred Reporting Items f...