British journal of anaesthesia
-
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.
-
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.