Background Intraoperative burst-suppression is associated with postoperative delirium. Whether this association is causal remains unclear. Therefore, the authors investigated whether burst-suppression during cardiopulmonary bypass (CPB) mediates the effects of known delirium risk factors on postoperative delirium. Methods This was a retrospective cohort observational substudy of the Minimizing ICU [intensive care unit] Neurological Dysfunction with Dexmedetomidine-induced Sleep (MINDDS) trial. The authors analyzed data from patients more than 60 yr old undergoing cardiac surgery (n = 159). Univariate and multivariable regression analyses were performed to assess for associations and enable causal inference. Delirium risk factors were evaluated using the abbreviated Montreal Cognitive Assessment and Patient-Reported Outcomes Measurement Information System questionnaires for applied cognition, physical function, global health, sleep, and pain. The authors also analyzed electroencephalogram data (n = 141). Results The incidence of delirium in patients with CPB burst-suppression was 25% (15 of 60) compared with 6% (5 of 81) in patients without CPB burst-suppression. In univariate analyses, age (odds ratio, 1.08 [95% CI, 1.03 to 1.14]; P = 0.002), lowest CPB temperature (odds ratio, 0.79 [0.66 to 0.94]; P = 0.010), alpha power (odds ratio, 0.65 [0.54 to 0.80]; P < 0.001), and physical function (odds ratio, 0.95 [0.91 to 0.98]; P = 0.007) were associated with CPB burst-suppression. In separate univariate analyses, age (odds ratio, 1.09 [1.02 to 1.16]; P = 0.009), abbreviated Montreal Cognitive Assessment (odds ratio, 0.80 [0.66 to 0.97]; P = 0.024), alpha power (odds ratio, 0.75 [0.59 to 0.96]; P = 0.025), and CPB burst-suppression (odds ratio, 3.79 [1.5 to 9.6]; P = 0.005) were associated with delirium. However, only physical function (odds ratio, 0.96 [0.91 to 0.99]; P = 0.044), lowest CPB temperature (odds ratio, 0.73 [0.58 to 0.88]; P = 0.003), and electroencephalogram alpha power (odds ratio, 0.61 [0.47 to 0.76]; P < 0.001) were retained as predictors in the burst-suppression multivariable model. Burst-suppression (odds ratio, 4.1 [1.5 to 13.7]; P = 0.012) and age (odds ratio, 1.07 [0.99 to 1.15]; P = 0.090) were retained as predictors in the delirium multivariable model. Delirium was associated with decreased electroencephalogram power from 6.8 to 24.4 Hertz. Conclusions The inference from the present study is that CPB burst-suppression mediates the effects of physical function, lowest CPB temperature, and electroencephalogram alpha power on delirium. Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New

Study Objective:Sleep is reflected not only in the electroencephalogram but also in heart rhythms and breathing patterns. Therefore, we hypothesize that it is possible to accurately stage sleep based on the electrocardiogram (ECG) and respiratory signals.Methods: Using a dataset including 8,682 polysomnographs, we develop deep neural networks to stage sleep from ECG and respiratory signals. Five deep neural networks consisting of convolutional networks and long short-term memory networks are trained to stage sleep using heart and breathing, including the timing of R peaks from ECG, abdominal and chest respiratory effort, and the combinations of these signals.Results: ECG in combination with the abdominal respiratory effort achieve the best performance for staging all five sleep stages with a Cohen's kappa of 0.600 (95% confidence interval 0.599 -0.602); and 0.762 (0.760 -0.763) for discriminating awake vs. rapid eye movement vs. non-rapid eye movement sleep. The performance is better for young participants and for those with a low apnea-hypopnea index, while it is robust for commonly used outpatient medications. Conclusions:Our results validate that ECG and respiratory effort provide substantial information about sleep stages in a large population. It opens new possibilities in sleep research and applications where electroencephalography is not readily available or may be infeasible, such as in critically ill patients. Deep Network ArchitectureWe trained five deep neural networks based on the following input signals and their combinations: 1) ECG; 2) CHEST (chest respiratory effort); 3) ABD (abdominal respiratory effort); 4) ECG+CHEST; and 5) ECG+ABD. Each deep neural network contained a feed-forward convolutional neural network (CNN) which learned features pertaining to each epoch, and a recurrent neural network (RNN), in this case long-short term memory (LSTM), to learn temporal patterns among consecutive epochs.The CNN of the network is similar to that in Hannun et al. 20 . As shown in Figure 1A and Figure 1B, the network for a single type of input signal, i.e. ECG, CHEST or ABD, consists of a convolutional layer, several residual blocks and a final output block. For a network with both ECG and CHEST/ABD as input signals ( Figure 1C), we first fixed the weights of the layers up to the 9 th residual block (gray) for the ECG network and similarly fixed up to the 5 th residual block (gray) for the CHEST/ABD network, concatenated the outputs, and then fed this concatenation into a subnetwork containing five residual blocks and a final output block. The numbers of fixed layers were chosen so that the outputs of layers from different modalities have the same shape (after padding zeros), and were then concatenated.The LSTM of the network has the same structure for different input signals. It is a bi-directional LSTM, where the context cells from the forward and backward directions are concatenated. For the network

Objective: This study aims to identify blood biomarkers of postoperative delirium. Background: Phosphorylated tau at threonine 217 (Tau-PT217) and 181 (Tau-PT181) are new Alzheimer disease biomarkers. Postoperative delirium is associated with Alzheimer disease. We assessed associations between Tau-PT217 or Tau-PT181 and postoperative delirium. Methods: Of 491 patients (65 years old or older) who had a knee replacement, hip replacement, or laminectomy, 139 participants were eligible and included in the analysis. Presence and severity of postoperative delirium were assessed in the patients. Preoperative plasma concentrations of Tau-PT217 and Tau-PT181 were determined by a newly established Nanoneedle technology. Results: Of 139 participants (73 ± 6 years old, 55% female), 18 (13%) developed postoperative delirium. Participants who developed postoperative delirium had higher preoperative plasma concentrations of Tau-PT217 and Tau-PT181 than participants who did not. Preoperative plasma concentrations of Tau-PT217 or Tau-PT181 were independently associated with postoperative delirium after adjusting for age, education, and preoperative Mini-Mental State score [odds ratio (OR) per unit change in the biomarker: 2.05, 95% confidence interval (CI):1.61-2.62, P < 0.001 for Tau-PT217; and OR: 4.12; 95% CI: 2.55--6.67, P < 0.001 for Tau-PT181]. The areas under the receiver operating curve for predicting delirium were 0.969 (Tau-PT217) and 0.885 (Tau-PT181). The preoperative plasma concentrations of Tau-PT217 or Tau-PT181 were also associated with delirium severity [beta coefficient (β) per unit change in the biomarker: 0.14; 95% CI: 0.09-0.19, P < 0.001 for Tau-PT217; and β: 0.41; 95% CI: 0.12-0.70, P = 0.006 for Tau-PT181). Conclusions: Preoperative plasma concentrations of Tau-PT217 and Tau-PT181 were associated with postoperative delirium, with Tau-PT217 being a stronger indicator of postoperative delirium than Tau-PT181.