Clinical Research Directory

The Accuracy and Efficacy of Large Language Model Written Hospital Course Summaries

Background: Physicians worldwide face an increasing administrative burden that diverts time from direct patient care. Among inpatient documentation tasks, authoring hospital course summaries is particularly time-consuming and critical for safe care transitions. Large language models (LLMs) have shown promise for clinical text generation; however, robust evidence from randomized, evaluator-blinded trials conducted in routine hospital practice remains limited. Objectives: The CLEAN study aims to evaluate whether LLM-assisted, specialistedited generation of hospital course summaries is non-inferior in safety compared with standard clinician-written documentation in routine inpatient care. Secondary objectives include noninferiority assessments of resident-edited and unedited LLMgenerated summaries. Additional objectives are to evaluate summary quality across predefined domains, quantify physician documentation time, assess LLM generation stability, measure clinician adoption following the randomized phase, and examine inter-, intra-observer, and test-retest reliability of expert assessments. Methods: This is a single-centre, double-campus, exploratory randomized controlled non-inferiority trial conducted at a tertiary university hospital. Consecutive hospital discharges across multiple clinical departments are randomized 1:1 to either an LLM-assisted documentation workflow or standard manual authorship. The intervention integrates an on-premise LLM into a parallel hospital information system, generating draft hospital course summaries from complete, uncurated clinical documentation, which physicians may review and edit prior to finalization. Safety, the primary outcome, defined as presence of all important information and absence of incorrect/hallucinated information, is assessed by an adjudication committee blinded to documentation workflow. Secondary outcomes include content validity, workflow efficiency, generation stability, post-trial clinician adoption, and reliability metrics. A total of 786 discharge episodes are required to assess non-inferiority using a predefined margin of 5 percentage points. Ethics and Dissemination: The study will be conducted in accordance with the Declaration of Helsinki, Good Clinical Practice, and the General Data Protection Regulation. A waiver of informed consent is sought due to minimal risk and exclusive use of routine clinical data. Results will be disseminated through peer-reviewed publication and engagement with healthcare stakeholders.

Prognostic Factors of Hospitalization for Patients Aged 75 and Over in Emergency Department in France - Monocentric Retrospective Cohort Study

A geriatric patient is defined as a patient aged 75 and over who meets certain medical or social vulnerability criteria and is characterised by coexisting physical and/or psychological dependence. The proportion of patients with a geriatric profile in the general population is growing. The average time spent in the emergency department by the elderly population is about 3 hours longer than for patients under 75 years old in France, which is associated with the risk of decompensation of chronic conditions, confusion, falls or agitation. An overnight stay in the emergency department for these patients increases the risk of mortality and the length of hospital stay. Several prognostic scores for hospitalization have been studied in adult populations. The most widely used scores are the Sydney Triage to Admission Risk Tool (START), the Ambulatory (AMB) and the Glasgow Admission Prediction Score (GAPS). Studies have compared these three scores and demonstrated the greater robustness of GAPS. The CalcuLation of the Elderly Admission Risk in the Emergency Department (CLEARED) tool, developed for the elderly population, has lower performance than GAPS. A systematic review of the literature studied the power of GAPS for the geriatric population and highlighted the need for validation in the target population. No validated hospitalization prognostic score was found in France for this population. The research hypothesis is that GAPS would detect hight probability of admission at the time of triage for the patients aged 75 and over in emergency department in France. The primary objective of this monocentric study is to evaluate the prognostic performance of GAPS for the target population (on the group 1). The secondary objectives consist of developing and internally validating a new score (PROFACTHOS) (on the group 2), then performing a temporal validation of PROFACTHOS with comparison to the GAPS (on the group 1), and finally to determine the threshold for classifying patients with a high probability of hospitalization for the score with the strongest discriminatory performance among GAPS or PROFACTHOS. Group 1: Patients aged 75 and over admitted to emergency department from 10/01/2024 to 09/30/2025. Group 2 : Patients aged 75 and over admitted to emergency department from 10/01/2022 to 09/30/2023

Frailty and Outcomes in Older Emergency Department Patients With Pneumonia

Pneumonia is one of the leading causes of infection-related mortality in the older population. Traditional severity scores used in emergency departments, such as the Pneumonia Severity Index (PSI) and CURB-65, primarily focus on acute physiological derangements and may not adequately capture biological reserve and frailty in older adults. Frailty is a geriatric syndrome reflecting increased vulnerability to stressors and reduced recovery capacity. This prospective observational cohort study aims to evaluate the predictive value of the Clinical Frailty Scale (CFS) for in-hospital mortality, 30-day mortality, and morbidity in patients aged 65 years and older presenting to the emergency department with pneumonia. Additionally, the study will assess whether incorporating frailty assessment into existing pneumonia severity scores improves prognostic accuracy.

French AKI Registry (FAKIR): A Multicenter Study on the In-Hospital Management and Outcomes of Severe Acute Kidney Injury in Nephrology Units

Acute Kidney Injury (AKI) is a common and serious condition in hospitalized patients, especially when it reaches stages 2 or 3 according to the KDIGO classification. These severe forms are associated with high mortality, a risk of progression to chronic kidney disease (CKD), and frequent cardiovascular complications. However, current data on how nephrologists manage these patients during hospitalization-and how these practices influence long-term outcomes-are limited and heterogeneous. The FAKIR study (French AKI Registry) is a prospective, multicenter, non-interventional observational study designed to describe the clinical management of patients admitted to nephrology departments for AKI stage 2 or 3 and to assess their renal and cardiovascular outcomes up to one year. The study hypothesizes that better characterization of in-hospital practices and patient trajectories will help identify predictors of renal recovery, progression to end-stage renal disease, and major cardiovascular events. Patients will be followed during hospitalization and at 3, 6, and 12 months to assess renal function, mortality, cardiovascular events, and rehospitalizations. This registry aims to provide real-life, multicenter data to support future guidelines and the development of structured post-AKI care pathways.

Inspiratory Muscle Training in Hospitalized Heart Failure Patients

Introduction Exercise intolerance is the most common symptom in patients with heart failure (HF), significantly impacting their quality of life and functional capacity. Muscle metabolism may be impaired due to sympathetic hyperactivation, systemic inflammation, and neurohormonal alterations, contributing to ventilatory inefficiency and exercise intolerance. Inspiratory muscle training (IMT) has been shown to improve inspiratory muscle strength and endurance, reducing fatigue and the sensation of dyspnea. There is a gap in the evidence regarding the use of IMT in hospitalized settings, particularly concerning short-term gains in inspiratory muscle strength and the safety of the intervention. This study aims to evaluate the effects of IMT on inspiratory muscle strength, hemodynamic and functional outcomes, as well as the safety of the IMT protocol in hospitalized patients with HF. Methods A randomized, controlled clinical trial will be conducted in the Cardiac Intensive Care Unit of the University Hospital Pedro Ernesto. The study will include individuals of both sexes, aged 18 years or older, who are hospitalized due to heart failure. Exclusion criteria will include: pregnancy; head trauma and/or brain injury; motor disability; signs and/or symptoms of low cardiac output; acute coronary syndrome; advanced HF with left ventricular ejection fraction (LVEF) below 20%; presence of untreated tachyarrhythmias or bradyarrhythmias; use of high-dose inotropes or vasopressors or an increase in their dose within the past 24 hours. Primary outcomes will include inspiratory muscle strength, safety, functional status, length of stay in the ICU, and hospital readmission within 90 days. After randomization, the intervention group will undergo IMT with a load between 30% and 50% of maximal inspiratory pressure (MIP), while the control group will perform IMT without load. It is expected that IMT will be safe and lead to improvements in inspiratory muscle strength and functional status, without significant hemodynamic repercussions.