Brit J Hosp Med
-
Aims/Background An artificial intelligence-assisted prediction model for enteral nutrition-associated diarrhoea (ENAD) in acute pancreatitis (AP) was developed utilising data obtained from bowel sounds auscultation. This model underwent validation through a single-centre, prospective observational study. The primary objective of the model was to enhance clinical decision-making by providing a more precise assessment of ENAD risk. ⋯ The area under the ROC curve was 0.904 (95% confidence interval: 0.817-0.997). Conclusion The artificial intelligence bowel sounds auscultation system enhances the assessment of gastrointestinal function in AP patients undergoing EN and facilitates the construction of an ENAD predictive model. The model demonstrates good predictive efficacy, offering an objective basis for precise intervention timing in ENAD management.
-
A 56-year-old male presented with a longstanding, gradually enlarging, painful, skin lesion over the natal cleft. This was initially thought to be a pilonidal abscess but, following multiple surgeries, he was diagnosed with Stage IVb squamous cell carcinoma of the natal cleft skin with bilateral inguinal lymph node metastases and subcutaneous metastatic deposits. Complete surgical cure was not possible. ⋯ His disease progressed, and he developed widespread metastases. He was thus transferred to palliative care with pain control being the major priority. He died within a year of diagnosis.
-
Aims/Background Reliable health-related quality of life data are critical in developing countries, in order to advocate for government agencies to develop national hemophilia care programmes. This study aims to explore the current status and influencing factors of health-related quality of life among adolescents with hemophilia in Hubei Province, so as to provide empirical data for professionals. Methods A total of 84 children with hemophilia aged 8 to 18, who were registered in Tongji Hemophilia Treatment Center and Hubei Hemophilia Home, were selected using a cluster sampling method. ⋯ The statistically significant influencing factors included residence, annual family income, and disease type. Conclusion This study provides empirical data support for the health management of adolescents with hemophilia, highlighting the importance of improving medical resource access, transfusion convenience, and psychological support in enhancing the quality of life for this group. The results emphasize the need for healthcare systems and policymakers to take specific measures to address these factors to improve the treatment and care conditions for adolescents with hemophilia.
-
Aims/Background Bedside ultrasound evaluation of venous excess ultrasound (VExUS) combined with the triglyceride-glucose (TyG) index plays an important role in predicting acute kidney injury (AKI) in patients with acute hyperlipidemic pancreatitis. VExUS can effectively evaluate the degree of venous congestion, while the TyG index is valuable in predicting severe pancreatitis. The combination of these two methods is expected to provide a more accurate AKI risk assessment tool for clinical practice. ⋯ Multiple logistic regression results showed that the TyG index and VExUS score were independent predictors of AKI in patients with acute hyperlipidemia pancreatitis (p < 0.05). The standard error, sensitivity and specificity of the TyG index, VExUS score and combined model for predicting AKI in these patients were 0.064, 73.91 and 87.45; 0.036, 78.16 and 95.65; 0.010, 100.00 and 95.65, respectively (p < 0.05). Conclusion The VExUS score combined with the TyG index is highly valuable in predicting AKI in patients with acute hyperlipidemic pancreatitis.
-
Aims/Background Sacroiliitis is a challenging condition to diagnose accurately due to the subtle nature of its presentation in imaging studies. This study aims to improve the diagnostic accuracy of sacroiliitis by applying advanced machine learning techniques to computed tomography (CT) images. Methods We employed five convolutional neural network (CNN) models-Visual Geometry Group 16-layer Network (VGG16), ResNet101, DenseNet, Inception-v4, and ResNeXt-50-to analyze a dataset of 830 CT images, including both sacroiliitis and non-sacroiliitis cases. ⋯ Grad-CAM visualizations offered insights into the decision-making processes, highlighting the models' focus on relevant anatomical features critical for accurate diagnosis. Conclusion The use of CNN models, particularly ResNeXt-50 and Inception-v4, significantly improves the diagnosis of sacroiliitis from CT images. These models not only provide high diagnostic accuracy but also offer transparency in their decision-making processes, aiding clinicians in understanding and trusting Artificial Intelligence (AI)-driven diagnostics.