British journal of anaesthesia
-
Letter Randomized Controlled Trial Comparative Study
Ultrasound-guided dynamic needle tip positioning versus conventional palpation approach for catheterisation of posterior tibial or dorsalis pedis artery in infants and small children.
-
The risk of complications, including death, is substantially increased in patients with pulmonary hypertension (PH) undergoing anaesthesia for surgical procedures, especially in those with pulmonary arterial hypertension (PAH) and chronic thromboembolic PH (CTEPH). Sedation also poses a risk to patients with PH. Physiological changes including tachycardia, hypotension, fluid shifts, and an increase in pulmonary vascular resistance (PH crisis) can precipitate acute right ventricular decompensation and death. ⋯ With an increasing number of patients requiring surgery in specialist and non-specialist PH centres, a systematic, evidence-based, multidisciplinary approach is required to minimise complications. Adequate risk stratification and a tailored-individualised perioperative plan is paramount.
-
Clinical Trial Observational Study
Deep learning models for the prediction of intraoperative hypotension.
Intraoperative hypotension is associated with a risk of postoperative organ dysfunction. In this study, we aimed to present deep learning algorithms for real-time predictions 5, 10, and 15 min before a hypotensive event. ⋯ Deep learning models can predict hypotensive events based on biosignals acquired using invasive and noninvasive patient monitoring. In addition, the model shows better performance when using combined rather than single signals.
-
Observational Study
Machine learning methods to improve bedside fluid responsiveness prediction in severe sepsis or septic shock: an observational study.
Passive leg raising (PLR) predicts fluid responsiveness in critical illness, although restrictions in mobilising patients often preclude this haemodynamic challenge being used. We investigated whether machine learning applied on transthoracic echocardiography (TTE) data might be used as a tool for predicting fluid responsiveness in critically ill patients. ⋯ Machine learning generated several models for predicting fluid responsiveness that were comparable with the haemodynamic response to PLR.