Conectar
Distal radius fractures account for one-fifth of all fractures in the active elderly population and may cause chronic pain, loss of hand function and reduced work productivity, imposing a significant socioeconomic burden. Most are initially treated with closed reduction and casting, but 30% subsequently require surgery due to insufficient realignment. The current approaches for analgesia for closed reduction are suboptimal. A brachial plexus nerve block provides complete pain relief and muscle relaxation distal to the elbow, potentially creating better conditions for realignment of the fractured bone ends. This may ultimately translate into reduced need for surgery and result in better functional outcomes and fewer complications compared to a haematoma block, which is the current standard care in Denmark.
The BLOCK Trial is an investigator-initiated, parallel-group, allocation-concealed, outcome assessor and analyst-blinded, superiority, randomised, controlled, clinical multicentre trial performed at 11 Danish emergency departments. Eligible adult patients with a distal radius fracture who need closed reduction will be included and allocated 1:1 to either an ultrasound-guided brachial plexus nerve block or a haematoma block. The primary outcome is the proportion of patients with distal radius fracture surgery 90 days after closed reduction. We will include 1716 participants to detect or discard a relative risk reduction of surgery of 20%. Secondary outcomes include treatment-related complications, patient-reported wrist function, pain during closed reduction and proportion of patients with unacceptable radiographic fracture position immediately after closed reduction.
The trial is approved by the Danish Medicines Agency and the Danish Research Ethics Committees (EU CT number: 2024-512191-35-00). All results will be summarised on www.theblocktrial.com, clinicaltrials.gov and euclinicaltrials.eu after publication. Primary and secondary outcome results from 0 to 90 days will be presented in the main article and submitted to a peer-reviewed journal. Results from outcomes on the 12-month follow-up will be presented separately.
Patient blood management (PBM), an evidence-based, patient-centred approach for optimising blood health, faces significant implementation challenges despite regulatory support, and this study explores its adoption within a Portuguese hospital to enhance education, develop tailored protocols and address healthcare system complexities, thereby contributing a unique perspective to the global discourse on PBM in Portuguese-speaking countries. This study will evaluate the clinical outcomes and cost-effectiveness of implementing a PBM programme in elective surgical patients at a tertiary Portuguese hospital, with secondary objectives focusing on preoperative anaemia prevalence and aetiology, PBM protocol adherence, transfusion practices guided by viscoelastic tests and the impact of cell salvage techniques.
A baseline evaluation will be conducted in 2018, and postintervention assessments will follow from 2019 to 2024. The control group comprised patients who underwent selected elective surgeries—including cardiac, general, orthopaedic, urological and gynaecological procedures—during 2018 without exposure to targeted PBM interventions. The intervention group consisted of patients scheduled for the same elective surgeries, who were referred for preanaesthesia evaluation to identify the need for PBM interventions. These interventions, where indicated, were implemented during the preoperative phase and extended to the intraoperative and postoperative periods to ensure a comprehensive and standardised approach to PBM application. Data will be extracted from pseudoanonymised medical records, ensuring full compliance with ethical standards and data protection regulations. Statistical analyses will be performed using robust methods suitable for categorical and continuous variables, enabling the evaluation of temporal trends and the overall effectiveness of PBM interventions in improving clinical outcomes.
Our research has been ethically approved by the Vila Nova de Gaia/Espinho Hospital Centre’s Ethical Health Committee (approval number 196/2023–1). We plan to disseminate our findings through posters, lectures at conferences and in scientific journals.
Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound analysis is promising. Explainable modelling can help its integration and acceptance in healthcare systems. We aim to develop an explainable AI model for analysing vascular wound images among an Asian population. Two thousand nine hundred and fifty-seven wound images from a vascular wound image registry from a tertiary institution in Singapore were utilized. The dataset was split into training, validation and test sets. Wound images were classified into four types (neuroischaemic ulcer [NIU], surgical site infections [SSI], venous leg ulcers [VLU], pressure ulcer [PU]), measured with automatic estimation of width, length and depth and segmented into 18 wound and peri-wound features. Data pre-processing was performed using oversampling and augmentation techniques. Convolutional and deep learning models were utilized for model development. The model was evaluated with accuracy, F1 score and receiver operating characteristic (ROC) curves. Explainability methods were used to interpret AI decision reasoning. A web browser application was developed to demonstrate results of the wound AI model with explainability. After development, the model was tested on additional 15 476 unlabelled images to evaluate effectiveness. After the development on the training and validation dataset, the model performance on unseen labelled images in the test set achieved an AUROC of 0.99 for wound classification with mean accuracy of 95.9%. For wound measurements, the model achieved AUROC of 0.97 with mean accuracy of 85.0% for depth classification, and AUROC of 0.92 with mean accuracy of 87.1% for width and length determination. For wound segmentation, an AUROC of 0.95 and mean accuracy of 87.8% was achieved. Testing on unlabelled images, the model confidence score for wound classification was 82.8% with an explainability score of 60.6%. Confidence score was 87.6% for depth classification with 68.0% explainability score, while width and length measurement obtained 93.0% accuracy score with 76.6% explainability. Confidence score for wound segmentation was 83.9%, while explainability was 72.1%. Using explainable AI models, we have developed an algorithm and application for analysis of vascular wound images from an Asian population with accuracy and explainability. With further development, it can be utilized as a clinical decision support system and integrated into existing healthcare electronic systems.
FreshRSS