Quality and efficiency of integrating customised large language model-generated summaries versus physician-written summaries: a validation study.

Objectives: To compare the quality and time efficiency of physician-written summaries with customised large language model (LLM)-generated medical summaries integrated into the electronic health record (EHR) in a non-English clinical environment.

Design: Cross-sectional non-inferiority validation study.

Setting: Tertiary academic hospital.

Operationalization of Artificial Intelligence Applications in the Intensive Care Unit: A Systematic Review.

Importance: Artificial intelligence (AI) presents transformative opportunities to address the increasing challenges faced by health care systems globally. Particularly, in data-rich environments, such as intensive care units (ICUs), AI could assist in enhancing clinical decision-making, streamline workflows, and improve patient outcomes. Despite these promising applications, the practical implementation of AI in clinical settings remains limited.

AI-generated draft replies to patient messages: exploring effects of implementation.

Introduction: The integration of Large Language Models (LLMs) in Electronic Health Records (EHRs) has the potential to reduce administrative burden. Validating these tools in real-world clinical settings is essential for responsible implementation. In this study, the effect of implementing LLM-generated draft responses to patient questions in our EHR is evaluated with regard to adoption, use and potential time savings.

Large language models in critical care.

The advent of chat generative pre-trained transformer (ChatGPT) and large language models (LLMs) has revolutionized natural language processing (NLP). These models possess unprecedented capabilities in understanding and generating human-like language. This breakthrough holds significant promise for critical care medicine, where unstructured data and complex clinical information are abundant.

Bridging the gap: a practical step-by-step approach to warrant safe implementation of large language models in healthcare.

Large Language Models (LLMs) offer considerable potential to enhance various aspects of healthcare, from aiding with administrative tasks to clinical decision support. However, despite the growing use of LLMs in healthcare, a critical gap persists in clear, actionable guidelines available to healthcare organizations and providers to ensure their responsible and safe implementation. In this paper, we propose a practical step-by-step approach to bridge this gap and support healthcare organizations and providers in warranting the responsible and safe implementation of LLMs into healthcare.

Comparative evaluation and performance of large language models on expert level critical care questions: a benchmark study.

Background: Large language models (LLMs) show increasing potential for their use in healthcare for administrative support and clinical decision making. However, reports on their performance in critical care medicine is lacking.

Methods: This study evaluated five LLMs (GPT-4o, GPT-4o-mini, GPT-3.

Methylene blue as treatment for vasoplegic shock in severe metformin overdose: A case report.

Introduction: Severe metformin overdose can result in life-threatening conditions such as metabolic acidosis with hyperlactatemia and vasoplegic shock. Current treatment guidelines recommend hemodialysis and supportive care. However, this case report presents the use of methylene blue as an additional treatment for severe metformin overdose-induced vasoplegic shock, which is not commonly described in the literature or guidelines.

Treatment implications of augmented renal clearance in a critically ill COVID-19 patient: A case report.

Augmented renal clearance (ARC) is a pathophysiological phenomenon that can occur in critically ill patients, leading to enhanced renal function. It is defined as a creatinine clearance of >130 mL/min/1.73 m .

The association between obesity and pressure ulcer development in critically ill patients: A prospective cohort study.

Background: Pressure ulcers (PUs) are one of the leading potentially preventable adverse events in the hospital. Critically ill patients are at risk for the development of PUs. The primary aim of the study was to investigate the relation of PUs and obesity in critically ill ICU patients.

[Medication during severe infections].

Severe infectious diseases result in an increased volume of distribution. Renal function is usually impaired, but can in fact be increased early in the course of the disease. In renally cleared drugs with a small therapeutic index a dose reduction should take place or these medications should be temporarily discontinued.

Considerations in Neuromuscular Blockade in the ICU: A Case Report and Review of the Literature.

Neuromuscular blocking agents are regularly used in the intensive care unit (ICU) to facilitate mechanical ventilation in patients with acute respiratory distress syndrome and patient-ventilator dyssynchronies. However, prolonged neuromuscular blockade is associated with adverse effects like ICU-acquired weakness. Residual neuromuscular blockade is, however, not routinely monitored in the intensive care unit, and as such, this phenomenon might be unrecognized and underreported.

Microbiological and immunological characteristics of a lethal pulmonary infection in a non-neutropenic patient.

Invasive pulmonary aspergillosis is increasingly described in non-neutropenic patients, such as patients with COPD receiving corticosteroids and the critically ill. Here, we present a case of a lethal pulmonary infection in a COPD patient. Immunological tests showed an impaired innate and adaptive immune response to .

Effect of preadmission sunlight exposure on intensive care unit-acquired delirium: a multicenter study.

Purpose: It is assumed that there is a relation between light exposure and delirium incidence. The aim of our study was to determine the effect of prehospital light exposure on the incidence of intensive care unit (ICU)-acquired delirium.

Materials And Methods: Data from 3 ICUs in the Netherlands were analyzed retrospectively.