Although anaesthesiologists strive to avoid hypoxemia during surgery, reliably predicting future intraoperative hypoxemia is not currently possible. Here, we report the development and testing of a machine-learning-based system that, in real time during general anaesthesia, predicts the risk of hypoxemia and provides explanations of the risk factors. The system, which was trained on minute-by-minute data from the electronic medical records of over fifty thousand surgeries, improved the performance of anaesthesiologists when providing interpretable hypoxemia risks and contributing factors. The explanations for the predictions are broadly consistent with the literature and with prior knowledge from anaesthesiologists. Our results suggest that if anaesthesiologists currently anticipate 15% of hypoxemia events, with this system’s assistance they would anticipate 30% of them, a large portion of which may benefit from early intervention because they are associated with modifiable factors. The system can help improve the clinical understanding of hypoxemia risk during anaesthesia care by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics.

Background-In the treatment of type B acute aortic dissection without complications, better results are obtained if surgery is performed before enlargement of the aorta in patients who are predicted to show aortic enlargement and if drug-based treatment is continued for patients who are predicted to show no enlargement. The purpose of this study was to predict the acute-phase factors that may affect chronic-phase aortic enlargement by studying chronic-phase enlargement of dissections in patients without complications during the acute phase. Methods and Results-In 101 patients with type B acute dissection who had no complications, univariate and multivariate factor analyses were performed to determine the predictors for chronic-phase enlargement (Ն60 mm) of the dissected aorta. The independent predominant predictors for aortic enlargement in the chronic phase were a maximum aortic diameter of Ն40 mm and a patent false lumen during the acute phase. The values of actuarial freedom from aortic enlargement for the patients with a maximum aortic diameter of 40 mm and a patent false lumen at 1, 5, and 10 years were 43%, 33%, and 22%, respectively, whereas in patients with a maximum aortic diameter of Ͻ40 mm and a closed false lumen, the values were 97%, 94%, and 84%, respectively. Conclusions-These results suggest that patients with type B acute aortic dissection who show a maximum aortic diameter of Ն40 mm and a patent false lumen should undergo surgery earlier during the chronic phase before enlargement of aorta, whereas patients with a maximum aortic diameter of Ͻ40 mm and a closed false lumen should continue to receive hypotensive therapy.

Opioids play a critical role in acute postoperative pain management. Our objective was to develop machine learning models to predict postoperative opioid requirements in patients undergoing ambulatory surgery. To develop the models, we used a perioperative dataset of 13,700 patients (� 18 years) undergoing ambulatory surgery between the years 2016-2018. The data, comprising of patient, procedure and provider factors that could influence postoperative pain and opioid requirements, was randomly split into training (80%) and validation (20%) datasets. Machine learning models of different classes were developed to predict categorized levels of postoperative opioid requirements using the training dataset and then evaluated on the validation dataset. Prediction accuracy was used to differentiate model performances. The five types of models that were developed returned the following accuracies at two different stages of surgery: 1

Artifacts are a significant problem affecting the accurate display of information during surgery. They are also a source of false alarms. A secondary problem is the inadvertent recording of artifactual and inaccurate information in automated record keeping systems. Though most of the currently available patient monitors use techniques to minimize the effect of artifacts, their success is limited. We reviewed the problem of artifacts affecting patient monitor data during surgical cases. Methods adopted by currently marketed patient monitors to eliminate and minimize artifacts due to technical and environmental factors are reviewed and discussed. Also discussed are promising artifact detection and correction methods that are being investigated. These might be used to detect and eliminate artifacts with improved accuracy and specificity.

We investigated the role of capacitative Ca(2+) entry and tyrosine kinase activation in mediating phenylephrine (PE)-induced oscillations in intracellular free Ca(2+) concentration ([Ca(2+)](i)) in canine pulmonary arterial smooth muscle cells (PASMCs). [Ca(2+)](i) was measured as the 340- to 380-nm ratio in individual fura 2-loaded PASMCs. Resting [Ca(2+)](i) was 96 +/- 4 nmol/l. PE (10 micromol/l) stimulated oscillations in [Ca(2+)](i), with a peak amplitude of 437 +/- 22 nmol/l and a frequency of 1.01 +/- 0.12/min. Thapsigargin (1 micromol/l) was used to deplete sarcoplasmic reticulum (SR) Ca(2+) after extracellular Ca(2+) was removed. Under these conditions, a nifedipine-insensitive, sustained increase in [Ca(2+)](i) (140 +/- 7% of control value) was observed when the extracellular Ca(2+) concentration was restored; i.e., capacitative Ca(2+) entry was demonstrated. Capacitative Ca(2+) entry also refilled SR Ca(2+) stores. Capacitative Ca(2+) entry was attenuated (32 +/- 3% of control value) by 50 micromol/l of SKF-96365 (a nonselective Ca(2+)-channel inhibitor). Tyrosine kinase inhibition with tyrphostin 23 (100 micromol/l) and genistein (100 micromol/l) also inhibited capacitative Ca(2+) entry to 63 +/- 12 and 85 +/- 4% of control values, respectively. SKF-96365 (30 micromol/l) attenuated both the amplitude (15 +/- 7% of control value) and frequency (50 +/- 21% of control value) of PE-induced Ca(2+) oscillations. SKF-96365 (50 micromol/l) abolished the oscillations. Tyrphostin 23 (100 micromol/l) also inhibited the amplitude (17 +/- 7% of control value) and frequency (45 +/- 9% of control value) of the oscillations. Genistein (30 micromol/l) had similar effects. Both SKF-96365 and tyrphostin 23 attenuated PE-induced contraction in isolated pulmonary arterial rings. These results demonstrate that capacitative Ca(2+) entry is present and capable of refilling SR Ca(2+) stores in canine PASMCs and may be involved in regulating PE-induced Ca(2+) oscillations. A tyrosine kinase is involved in the signal transduction pathway for alpha(1)-adrenoreceptor activation in PASMCs.