Coronary artery involvement remains the primary focus in the long-term management of Kawasaki disease (KD). However, previous studies suggest that myocardial abnormalities frequently persist beyond coronary artery involvement in KD patients. Yet, their temporal evolution and clinical implications remain poorly characterised. To address this gap, we established the Kawasaki disease cardiac imaging (KDCI) cohort, integrating cardiac magnetic resonance (CMR) with echocardiography, coronary CT angiography (CCTA) and invasive angiography. These multimodal imaging approaches enable comprehensive assessment of cardiac abnormalities and elucidate the role of cardiac imaging in optimising long-term KD management.

The KDCI cohort is a prospective study aiming to enrol 400–500 KD patients diagnosed at West China Second University Hospital from September 2018 to September 2035. To date, 207 participants have been recruited. Participants will perform the multimodal cardiac imaging including echocardiography, CMR, CCTA, invasive angiography and comprehensive laboratory testing under a scheduled protocol in the follow-up.

The KDCI cohort has established baseline characteristics for 207 KD patients. Of those included to date, 72.0% (149/207) received intravenous immunoglobulin (IVIG) treatment, with 26.1% (54/207) demonstrating IVIG resistance, and 37.7% (78/207) exhibiting coronary artery dilatation. Longitudinal follow-up data are available for 80.7% (167/207) of participants, with a median follow-up duration of 2.7 years and a follow-up patient-years of 594 patient-years. Of the 207 patients, 16.9% (35/207) patients experienced endpoint events, encompassing coronary artery thrombosis (8.2%, 17/207), coronary stenosis/obstruction (5.3% 11/207) and clinical myocardial infarction (1.9%, 4/207). Based on the data collected, we have demonstrated the cardiac abnormalities beyond coronary artery involvement in KD by CMR and CCTA.

The KDCI cohort will maintain ongoing recruitment and longitudinal follow-up, with a projected enrolment exceeding 400 participants by 2035. This expansion will yield a median follow-up duration of 10 years, providing robust long-term outcome data. We have implemented standardised protocols for scheduled follow-up assessments and data collection in newly enrolled patients. Furthermore, planned genomic analyses will be incorporated to investigate the molecular pathogenesis and prognostic determinants of KD.

Postoperative delirium is a serious complication occurring in 10.09%–51.28% of geriatric patients undergoing surgery for hip fractures. Delirium has resulted in poorer functional recovery, increased readmission rates, repeat surgeries and elevated mortality. Perioperative music listening is a promising non-pharmacological intervention with beneficial effects on delirium. This trial aims to evaluate the effect of perioperative music listening on postoperative delirium in patients with femur fracture undergoing surgery.

The music listening on clinical outcome after hip fracture operations study is an investigator-initiated, randomised controlled, clinical trial. 102 patients with femur fracture meeting eligibility criteria will be randomised to the music listening intervention or control group with concealed allocation. The perioperative music intervention consists of preselected lists totalling 4 hours of music (classical, jazz and pop). The primary outcome is postoperative delirium rate. Secondary outcome measures include pain score and opioid medication requirement, postoperative complications, hospital length of stay, 14-day readmission rate and 30-day mortality. A 90-day follow-up will be performed in order to assess readmission rate and mortality rate. Data will be analysed according to an intention-to-treat principle.

The study protocol was approved by the Research Ethics Committee of Ditmanson Medical Foundation of Chia-Yi Christian Hospital (IRB2023084). The trial will be carried out following the Declaration of Helsinki principles and Good Clinical Practice guidelines. Research data will be reported following Consolidated Standards of Reporting Trials guidelines and study results will be published in a peer-reviewed journal and presented at scientific conferences. Data availability statement: data generated by this study will be made available on reasonable request. A data sharing plan has been submitted to ClinicalTrials.gov in compliance with ICMJE (International Committee of Medical Journal Editors) and BMJ Open data policies.

NCT06209788.

Artificial intelligence (AI), defined as the simulation of human intelligence in machines designed to replicate human cognitive processes, is becoming increasingly prevalent in nursing practice and research. Recent reviews have examined the application of AI across various nursing domains, highlighting its role in clinical decision support, administrative efficiency and educational advancements.1 2

AI techniques, including machine learning and natural language processing, are being employed to address a range of clinical, managerial and educational challenges in nursing.2–4 These advancements have demonstrated potential in improving patient monitoring, optimising workload distribution and supporting clinical decision-making.2 5 However, despite AI’s increasing presence in nursing practice, a structured framework guiding its integration remains non-existent.

Machine learning, a core component of AI, is instrumental in various nursing applications. It enables pattern recognition and predictive analysis through the examination of...