British journal of anaesthesia
-
Continuous real-time prediction of surgical case duration using a modular artificial neural network.
Real-time prediction of surgical duration can inform perioperative decisions and reduce surgical costs. We developed a machine learning approach that continuously incorporates preoperative and intraoperative information for forecasting surgical duration. ⋯ A real-time neural network model using preoperative and intraoperative data had significantly better performance than a Bayesian approach or scheduled duration, offering opportunities to avoid overtime labour costs and reduce the cost of surgery by providing superior real-time information for perioperative decision support.
-
Quantitative pupillometry is recommended for neuroprognostication after out-of-hospital cardiac arrest 72 h or more after ICU admission, but the feasibility and utility of earlier assessment is unknown. ⋯ Quantitative pupillometry within 6 h of ICU admission after out-of-hospital cardiac arrest may identify patients with a very low chance of neurologically intact survival. Further studies of early quantitative pupillometry in this population are warranted.
-
The adverse haemodynamic effects of the intravenous anaesthetic propofol are well known, yet few empirical models have explored the dose-response relationship. Evidence suggests that hypotension during general anaesthesia is associated with postoperative mortality. We developed a mechanism-based model that quantitatively characterises the magnitude of propofol-induced haemodynamic effects during general anaesthesia. ⋯ NCT02043938.
-
Conventional patient vital signs monitoring fails to detect many signs of patient deterioration, including those in the critical postoperative period. Wearable monitors can allow continuous vital signs monitoring, send data wirelessly to the electronic healthcare record, and reduce the number of unplanned admissions to intensive care.