Health

626 stories · page 37 of 42

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

Performance evaluation of five major large language models in tuberculosis Q&A systems: A multidimensional assessment of readability, quality, and reliability

Both readings

Mapping artificial intelligence integration in objective structured clinical examinations: A scoping review

Both readings

Combining pathology artificial intelligence and genomic biomarkers to refine long-term postprostatectomy outcome prediction

Both readings

Improving turnaround times with artificial intelligence in microbiology

This dual-center study evaluated the impact of artificial intelligence (AI) on urine culture turnaround times in Canadian diagnostic laboratories using microbiology laboratory automation. Data were collected before and after the implementation of PhenoMATRIX (PM), an AI-based software that provides continuous culture sorting and result interpretation support. In both a low-volume tertiary care hospital and a high-volume community laboratory, PM enabled earlier availability of interpretable results; however, redu…

Both readings

Artificial Intelligence for Evidence Synthesis of Emerging Biologics to Improve Skeletal Health in Osteogenesis Imperfecta: Systematic Review and Meta-Analysis

Background: Osteogenesis imperfecta (OI) is a rare genetic disorder characterized by bone fragility and recurrent fractures. Emerging biologics demonstrate promise by targeting bone-remodeling pathways, yet evidence for their efficacy and safety remains fragmented and heterogeneous, and no prior systematic review in OI has incorporated artificial intelligence (AI) to synthesize it. Objective: This study aims to systematically evaluate the efficacy and safety of novel biologics in patients with OI using an AI-ass…

Both readings

Beyond EuroSCORE II: is artificial intelligence ready to redefine risk stratification in cardiothoracic surgery?

Risk stratification is central to contemporary cardiothoracic surgical practice, guiding patient selection, perioperative planning, informed consent, and benchmarking of outcomes across institutions. Established models such as European System for Cardiac Operative Risk Evaluation II and the Society of Thoracic Surgeons risk score remain widely used because they are validated, interpretable, and embedded within routine clinical workflows. However, their static structure and reliance on predefined variables may li…

Model-prefilled problem

Beyond the algorithm: health technology assessment frameworks for AI in cardiology under the European Union Health Technology Assessment Regulation: a systematic review

Background: Artificial intelligence (AI) is increasingly used in cardiovascular care to support diagnosis, monitoring and clinical decision-making. However, its dynamic and adaptive nature challenges conventional health technology assessment (HTA) frameworks, which are typically designed for static interventions. This review aims to assess how existing literature supports HTA-relevant evaluation of AI-based cardiovascular technologies and examine their alignment with the evidentiary requirements outlined in the…

Health

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

Objective To evaluate red-flag recognition, clinical safety, and the quality of patient actionability in responses generated by artificial intelligence (AI) chatbots to patient questions about nipple discharge. Methods This guideline-informed cross-sectional evaluation was conducted to assess the performance of AI chatbots in simulated nipple discharge consultations. A total of 36 English-language simulated patient questions were developed on the basis of clinical guidelines and real-world consultation scenarios…

Health

Quantifying the impact of slice thickness on cardiovascular risk stratification in lung cancer screening: a multi-center "RESCUE" study

Background: Patients undergoing routine non-gated chest computed tomography (CT) for health checkups or atypical chest discomfort often present with a coronary artery calcium (CAC) score of zero on standard 5.0 mm reconstructions. We hypothesized that these thick slices obscure mild calcification due to partial volume effects (PVEs), which could be recovered by retrospective analysis of native thin-slice images. This study aimed to quantify the rate of unrecognized coronary calcification on standard thick-slice…

Health

Embedded transparency in artificial intelligence: a prerequisite for equity and representation in AI-enabled clinical trials

Artificial intelligence is being embedded in clinical trial infrastructure, shaping who is identified, stratified, and analysed. Opaque models risk amplifying existing disparities in the evidence base. We argue that embedded transparency, the structural integration of ex ante interpretability, demographic auditability, documented uncertainty handling, and stakeholder-relative explanation, is a necessary, though not sufficient, condition for equitable AI-enabled trials, and propose governance recommendations acti…

Health

Performance evaluation of domain-specific and general-purpose AI models for chest radiograph interpretation: a comparative study

Chest radiography remains the most widely used imaging modality worldwide; however, its interpretation is inherently challenging because of overlapping anatomical structures and subtle findings. Recent advances in multimodal large language models (LLMs) have enabled automated radiology report generation, yet their clinical performance relative to domain-specific medical AI systems remains insufficiently validated. This study aimed to evaluate the performance and clinical applicability of a domain-specific multim…

Health

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

Artificial intelligence (AI) has rapidly emerged as a transformative force in radiology, offering enhanced diagnostic accuracy, workflow optimization, and the potential to alleviate rising imaging demands. As radiology remains inherently dependent on pattern recognition and high-volume data interpretation, it represents an ideal domain for AI integration. This narrative review synthesizes current evidence on the clinical impact of AI across multiple dimensions of radiologic practice, including diagnostic perform…

Health

Adopting AI Enhances Humanitarian Operations While Demanding Critical Trade-Offs

Artificial intelligence (AI) is increasingly impacting the cooperation sector, transforming how humanitarians are operating in the field. AI tools now allow for improved health diagnostics and quality services. In conflict areas, organizations are able to improve the efficiency of their analysis, and propose optimized data management processes for more multifactorial predictions. In a context where human and financial resources are limited, AI address the gaps to sustain emergency responses. In this commentary,…

Health

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

Effective handoff communication between the emergency department and inpatient units is essential for patient safety and nurse well-being. This project uses an innovative design strategy and generative artificial intelligence to improve the quality and consistency of information exchanged during nurse-to-nurse handoffs. By generating computer-based summaries, key patient details can be accurately conveyed, reducing the need for manual review and customization. Developed through a collaborative hackathon with fro…