Journal of clinical monitoring and computing
-
J Clin Monit Comput · Dec 2024
Prediction of intraoperative hypotension using deep learning models based on non-invasive monitoring devices.
Intraoperative hypotension is associated with adverse outcomes. Predicting and proactively managing hypotension can reduce its incidence. Previously, hypotension prediction algorithms using artificial intelligence were developed for invasive arterial blood pressure monitors. This study tested whether routine non-invasive monitors could also predict intraoperative hypotension using deep learning algorithms. ⋯ A deep learning model utilizing multi-channel non-invasive monitors could predict intraoperative hypotension with high accuracy. Future prospective studies are needed to determine whether this model can assist clinicians in preventing hypotension in patients undergoing surgery with non-invasive monitoring.
-
J Clin Monit Comput · Dec 2024
Letter Case ReportsProne-position decreases airway closure in a patient with ARDS undergoing venovenous extracorporeal membrane oxygenation.
Airway closure is a interruption of communication between larger and smaller airways. The presence of airway closure during mechanical ventilation may lead to the overestimation of driving pressure (DP), introducing errors in the assessment of respiratory mechanics and in positive end-expiratory pressure (PEEP) setting on the ventilator. Patients with severe acute respiratory distress syndrome (ARDS) may exhibit the airway closure phenomenon, which can be easily diagnosed with a low-flow inflation. Prone positioning is a therapeutic manoeuver proven to reduce mortality in ARDS patients, and has been widely implemented also in patients requiring veno-venous extracorporeal membrane oxygenation (V-V ECMO). To date, the impact of prone positioning on changes in airway closure has not been described. ⋯ Prone positioning reduced airway closure in an ARDS patient on VV ECMO support.