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.

Cross-sectional non-inferiority validation study.

Tertiary academic hospital.

52 physicians from 8 specialties at a large Dutch academic hospital participated, either in writing summaries (n=42) or evaluating them (n=10).

Physician writers wrote summaries of 50 patient records. LLM-generated summaries were created for the same records using an EHR-integrated LLM. An independent, blinded panel of physician evaluators compared physician-written summaries to LLM-generated summaries.

Primary outcome measures were completeness, correctness and conciseness (on a 5-point Likert scale). Secondary outcomes were preference and trust, and time to generate either the physician-written or LLM-generated summary.

The completeness and correctness of LLM-generated summaries did not differ significantly from physician-written summaries. However, LLM summaries were less concise (3.0 vs 3.5, p=0.001). Overall evaluation scores were similar (3.4 vs 3.3, p=0.373), with 57% of evaluators preferring LLM-generated summaries. Trust in both summary types was comparable, and interobserver variability showed excellent reliability (intraclass correlation coefficient 0.975). Physicians took an average of 7 min per summary, while LLMs completed the same task in just 15.7 s.

LLM-generated summaries are comparable to physician-written summaries in completeness and correctness, although slightly less concise. With a clear time-saving benefit, LLMs could help reduce clinicians’ administrative burden without compromising summary quality.

Guidelines for symptomatic knee osteoarthritis (OA) dictate the initiation of conservative treatment (physical therapy, analgesics and intra-articular injections with corticosteroids) as a first line defence. When conservative treatment fails, the golden standard is invasive joint replacement surgery, but for a substantial group of patients who do not respond to the current conservative treatment, this is not (yet) indicated. The RADIOPHENOL study investigates if denervation of knee sensory (genicular) nerves can serve the gap between conservative and invasive treatment for younger patients and for patients who cannot undergo joint replacement surgery due to comorbid health conditions.

The RADIOPHENOL study is a multicentre unblinded randomised controlled trial with three parallel arms (1:1:1). In total, 192 patients with knee OA Kellgren-Lawrence grades 2–4 but not eligible for joint replacement according to the orthopaedic surgeon due to young age, old age and/or comorbidity or technical reasons are eligible and will be randomised to three groups of 64 patients. Group A: traditional radiofrequency ablation, group B: chemical neurolysis with phenol, group C: conservative medical management. Primary outcome is the Oxford Knee Score at 6 months. Secondary outcomes include Western Ontario and McMaster Universities Osteoarthritis Index, knee pain by numeric rating scale, physical functionality, health-related quality of life, mental health, change in medication use, predictive value of a diagnostic block, procedure time, patient discomfort score during the intervention and adverse events.

The protocol (V.2.0, 15 May 2023), was approved by the Ethics Committee of Amsterdam UMC (NL83410.018.22 – METC2022.0890) on 31 July 2023. We aim to publish our results in international peer-reviewed journals.

ClinicalTrials.gov NCT06094660, including the WHO Trial Registration data set items. Registered on 20 October 2023, first patient enrolled on 27 November 2023.

Urinary tract infections (UTIs) are highly prevalent and pose a significant burden among older adults. Accurate diagnosis in this population is challenging due to the high prevalence of pre-existing lower urinary tract symptoms, inability to express symptoms and asymptomatic bacteriuria. Current diagnostic tests are unreliable, often resulting in over- and underdiagnosis. A previous pilot study proposed a higher cut-off for pyuria and identified five promising biomarkers for the diagnosis of UTIs in older adults. The UTI-GOLD study aims to validate these five new biomarkers and the higher leucocyte cut-off as a diagnostic tool for UTIs in older people in a real-world setting.

Between August 2024 and December 2027, an observational multicentre diagnostic accuracy study is being conducted across primary, secondary and tertiary healthcare facilities in the Netherlands and the UK. Adults ≥65 years with a suspected UTI will be considered eligible. Patients with pre-existing decision-making incapacity or an indwelling catheter will be excluded. UTI will be defined according to an international consensus-based reference standard. Biomarkers will be measured by liquid chromatography-mass spectrometry (neutrophil gelatinase-associated lipocalin, tissue inhibitor of metalloproteinase 2 and CXC motif chemokine ligand 9) and enzyme-linked immunosorbent assay (interleukin 6 and azurocidin). Pyuria will be quantified by automated microscopy and/or flow cytometry. Diagnostic accuracy measures will be calculated using the receiver operating characteristic curves, and sensitivity, specificity, likelihood ratios and predictive values will be reported for optimal cut-offs.

The protocol was reviewed by the local Leiden University Medical Center research committee, who declared on 15 April 2024 that the medical research involving human subject act (Dutch abbreviation: WMO) does not apply to the current study (reference number nWMODIV2_2024025). The study also received approval from the NHS Research Ethics Committee in the UK (reference number 24/LO/0649).

The study findings will be published in a peer-reviewed journal, presented at academic congresses and shared with healthcare providers.

The study was registered at clinicaltrial.gov on the 24 September 2024 with registration number: NCT06610721.

Prompt recognition and treatment of patients with sepsis improve survival. Patients transported to hospital with sepsis often do not receive treatment until they are assessed in emergency departments. Initiation of treatments by paramedics at the point of first contact may improve outcomes for these patients.

The study design involves two randomised controlled trials (RCTs) conducted using a 2x2 factorial design comparing use of (1) early intramuscular ceftriaxone versus placebo and (2) an early liberal intravenous fluid strategy (up to 2 L normal saline) versus usual care resuscitation guided by paramedic medical directives. Patients who are ≥18 years of age will be eligible for inclusion if they have sepsis, defined as (1) paramedic suspicion of infection, (2) fever (temperature ≥38.0°C measured by paramedic or history of fever during the previous 24 hours), and (3) hypotension: SBP 250 mL) within 24 hours of hospital arrival; total amount of crystalloid infused during transport and first 24 hours of hospitalisation; and proportion of enrolled patients not suspected to have sepsis or infection by emergency department physicians. Safety outcomes include the proportion of patients with pulmonary oedema during transport to hospital and on initial chest X-ray and the proportion of patients with anaphylaxis or suspected allergic reactions to study medication.

This study has been approved through Clinical Trials Ontario’s streamlined ethics review process (board of record, Sunnybrook Health Sciences Centre). It will be conducted in accordance with the Declaration of Helsinki, Good Clinical Practice guidelines and regulatory requirements. The final results will be disseminated to participating paramedic services through educational materials, presentations and interactive training. We anticipate our trial will achieve wide dissemination through publication in a peer-reviewed medical journal and presentation at international conferences targeting the fields of prehospital and emergency medicine, resuscitation and critical care.

NCT03068741.

Children with Medical Complexities (CMC) often require 24/7 expert care, which frequently necessitates prolonged (re)admissions to a university medical centre (UMC), thereby impeding discharge to home. The transition from hospital to home for CMC is a multifaceted process with numerous challenges and obstacles. This protocol describes the evaluation of an innovative transitional care unit (TCU), where families can stay together in a home-like environment between hospital and home. Under the supervision of healthcare professionals, parents are supported in preparing for a sustainable home situation. We hypothesise that an intermediate stay at the Jeroen Pit Huis (JPH) will have a favourable effect on healthcare consumption, patient, parent and family-relevant outcomes in comparison to discharge directly from a hospital ward to home. Therefore, the purpose of this study is to compare the transition via the TCU JPH versus transition from hospital ward to home as provided elsewhere for CMC patients in the Netherlands.

This observational prospective cohort study compares patients who transition directly from hospital to home with those who transition via the TCU. The control group comprises five UMCs in the Netherlands. Data will be collected by extracting information from electronic health records and through online questionnaires. Parents complete questionnaires at three time points: on discharge home, 3 months and 12 months postdischarge. Bayesian inverse probability weighting will be used to control for confounding effects and analyse the results.

Ethical approval was granted by the Amsterdam UMC Medical Ethics Committee (W20_220#20.007). The need for ethical approval was waived by all other participating UMCs. Results will be disseminated through peer-reviewed scientific journals and conference presentations. The insights gained from this study will contribute to the development of a national care pathway to enhance transitional care for CMC and their families in the future.

NCT06599398 (ClinicalTrials.gov) - Bridging Hospital to Home for CMC and Their Families.