Background The discrepancy between predicted effect-site concentration and measured bispectral index is problematic during intravenous anesthesia with target-controlled infusion of propofol and remifentanil. We hypothesized that bispectral index during total intravenous anesthesia would be more accurately predicted by a deep learning approach. Methods Long short-term memory and the feed-forward neural network were sequenced to simulate the pharmacokinetic and pharmacodynamic parts of an empirical model, respectively, to predict intraoperative bispectral index during combined use of propofol and remifentanil. Inputs of long short-term memory were infusion histories of propofol and remifentanil, which were retrieved from target-controlled infusion pumps for 1,800 s at 10-s intervals. Inputs of the feed-forward network were the outputs of long short-term memory and demographic data such as age, sex, weight, and height. The final output of the feed-forward network was the bispectral index. The performance of bispectral index prediction was compared between the deep learning model and previously reported response surface model. Results The model hyperparameters comprised 8 memory cells in the long short-term memory layer and 16 nodes in the hidden layer of the feed-forward network. The model training and testing were performed with separate data sets of 131 and 100 cases. The concordance correlation coefficient (95% CI) were 0.561 (0.560 to 0.562) in the deep learning model, which was significantly larger than that in the response surface model (0.265 [0.263 to 0.266], P < 0.001). Conclusions The deep learning model–predicted bispectral index during target-controlled infusion of propofol and remifentanil more accurately compared to the traditional model. The deep learning approach in anesthetic pharmacology seems promising because of its excellent performance and extensibility.

Double-lumen tube placement with the patient in the supine position without a headrest minimizes displacement during lateral positioning La mise en place d'une sonde à double lumière chez un patient en decubitus dorsal sans appuie-tête minimise le risque de déplacement au cours du passage en decubitus latéral Abstract Purpose The correct position of double-lumen tubes (DLTs) is customarily confirmed after tracheal intubation by bronchoscopy with the patient supine on a headrest. However, displacement of DLTs usually occurs during lateral positioning because of neck extension. This study was undertaken to determine whether displacement of DLTs could be minimized during lateral positioning if DLTs were positioned without a headrest. Methods One hundred patients scheduled for thoracic surgery were randomized into two groups (n = 50 each). After tracheal intubation using a headrest, adjustment of DLT position was performed according to group assignment, i.e., either with the headrest in place or without the headrest. Using a bronchoscope, distances from the tracheal opening to the main carina and from the bronchial opening to the left bronchial carina were measured in both the supine and lateral positions. Results Displacement of DLTs [mean (standard deviation)] during lateral positioning was greater in the headrest group than in the no-headrest group [12.3 (6.5) mm vs 6.8 (5.5) mm, respectively, in the trachea; 11.6 (6.7) mm vs 6.0 (4.6) mm, respectively, in the bronchus; P \ 0.001]. The incidence of significant displacement, defined as [ 10 mm from initial correct position, was greater in the headrest group than in the no-headrest group (64% vs 28%, respectively, in the trachea; 58% vs 20%, respectively, in the bronchus; P \ 0.001). Conclusion Displacement of DLTs during lateral positioning appears to be caused primarily by extension of the neck. Correct adjustment of DLT position without a headrest in the supine position is an easy and effective method to minimize DLT displacement during lateral positioning (ClinicalTrials.gov number, NCT01413347). RésuméObjectif La bonne position des sondes a`doubles lumie`res (DLT) est d'ordinaire confirme´e par bronchoscopie apre`s intubation trache´ale chez un patient en decubitus dorsal avec appuie-teˆte. Cependant, ces sondes se de´placent habituellement au cours d'un changement de position en decubitus late´ral en raison d'une extension du cou. Cette e´tude a e´te´entreprise pour de´terminer si le de´placement des DLT pouvait eˆtre minimise´au cours d'un passage en This article is accompanied by an editorial, please see Can J Anesth 2012; 59: this issue.

Hematocrit measured using the POC device tends to be lower than the laboratory hematocrit measured during LT. Commonly encountered laboratory abnormalities during LT include hypoalbuminemia, hypoproteinemia, and hyperglycemia, which may contribute to falsely low-measured POC hematocrit. Careful consideration of these confounders may help reduce overtransfusion that occurs due to falsely low-measured POC hematocrit.

EMR without BM involvement after allogeneic HSCT is extremely rare, especially in children; only a few cases have been reported. A two-yr-old boy was diagnosed with AML (M4) and underwent allogeneic HSCT in first complete remission with BM from HLA-matched unrelated donor without GVHD. Four yr later, he had a BM relapse and after induction and consolidation chemotherapy, he received a second HSCT from an unrelated donor using peripheral blood stem cells. His second post-transplant course was complicated by extensive chronic GVHD involving the skin, oral cavity, and lungs, which was treated with tacrolimus and corticosteroid. Two yr later, he noticed a mild swelling in the right cheek area. The BM showed a complete remission marrow and a soft tissue biopsy was compatible with granulocytic sarcoma. PET-CT showed multifocal bone involvements. He received chemotherapy, and the chloromas decreased in size. We report a case of diffuse EMR of AML without BM involvement after a second allogeneic HSCT.