Brit J Hosp Med
-
The rapidly developing field of artificial intelligence (AI) may soon equip clinicians with algorithms that model and predict perioperative problems with extreme accuracy. Here, we outline emerging AI applications in preoperative risk stratification and intraoperative event prediction, where algorithm performance has been shown to outstrip commonly used conventional risk prediction tools. While offering an enticing view of a novel perioperative practice with superhuman foresight, AI's limited scope and lack of transparency remain key challenges for widespread adoption. As yet it is unclear whether machine learning alone can influence human clinical practice to exert real-world effects on patient outcomes.
-
Randomized Controlled Trial
Clinical Effect of Personalized Adjustable Mandibular Advancement Device on Obstructive Sleep Apnea.
Aims/Background: Mandibular advancement devices are effective in treating mild or moderate obstructive sleep apnea (OSA), but such devices that are commonly used in clinical settings require further improvement. In this study, we evaluated the clinical effects of personalized adjustable mandibular advancement devices on mild or moderate OSA. Methods: Forty patients with mild or moderate OSA were randomly divided into experimental (personalized adjustable device) and control (traditional device) groups. ⋯ Soft palate- and tongue-pharyngeal cross-sectional areas were significantly increased in both groups, but temporomandibular joint morphology or motion trajectory remained unchanged. Conclusion: The personalized adjustable mandibular advancement devices may reduce side effects and are effective in treating patients with OSA. Clinical Trial Registration: The study was registered and approved by the Chinese Clinical Trial Registry (ChiCTR2400080306). https://www.chictr.org.cn/showproj.html?proj=206538.
-
Aims/Background: The coronavirus disease 2019 (COVID-19) pandemic has highlighted the need for accurate and efficient diagnostic methods. This study aims to improve COVID-19 detection by integrating chest X-ray (CXR) and computerized tomography (CT) images using deep learning techniques, further improving diagnostic accuracy by using a combined imaging approach. Methods: The study used two publicly accessible databases, COVID-19 Questionnaires for Understanding the Exposure (COVID-QU-Ex) and Integrated Clinical and Translational Cancer Foundation (iCTCF), containing CXR and CT images, respectively. ⋯ The EfficientNet-based models, with their superior feature extraction capabilities, show better performance than ResNet models. Grad-CAM Visualizations provide insights into the model's decision-making process, potentially reducing diagnostic errors and accelerating diagnosis processes. This approach can improve patient care and support healthcare systems in managing the pandemic more effectively.
-
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 Backward walking is gaining traction in rehabilitation therapy, showing promise as an intervention for stroke patients with walking difficulties. However, the brain activity patterns (neurophysiological mechanisms) underlying backward walking in these patients remain unclear. This study investigated the neurophysiological mechanism in stroke patients within 1 year of their stroke. ⋯ Additionally, the DAR was significantly lower during backward walking than during forward walking (p < 0.05). Conclusion This study suggests that backward walking may more effectively activate neural activity in the prefrontal and right posterior parietal cortices. This finding supports the potential of backward walking to enhance motor execution and walking function in stroke patients, thereby supporting its application as a rehabilitation method.