Chie Nagata

Postoperative delirium (POD) is associated with complications following cardiovascular surgery, and its psychomotor subtypes differ in clinical course and treatment responsiveness, underscoring the importance of personalized preventive strategies. We aimed to investigate preoperative neurophysiological characteristics associated with POD and its psychomotor subtypes in patients undergoing cardiovascular surgery. This prospective, single-center study included 209 patients undergoing cardiovascular surgery. Preoperative frontal electroencephalography (EEG) was recorded using a patch-type device with three electrodes (left, center, and right). Standardized mean power spectral density of the following frequency bands was calculated: theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), gamma1 (30–59 Hz), and gamma2 (61–75 Hz). Delirium and its psychomotor subtypes were assessed until postoperative day 7. EEG features were compared between patients with and without POD and among psychomotor subtypes, with adjustment for multiple comparisons. POD occurred in 70 patients (33.5%). No significant differences in preoperative EEG power were observed between patients with and without POD. However, patients with the hyperactive-or-mixed subtype demonstrated significantly higher theta and lower alpha activity than those with the hypoactive or no motor subtypes. These findings may identify neurophysiological markers associated with underlying psychomotor symptoms in delirium and may inform preoperative subtype risk stratification. Trial registration: UMIN-CTR (ID: UMIN000049390).

Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict post-cardiovascular surgery delirium. Patients aged ≥ 40 years who underwent cardiovascular surgery at a single hospital were prospectively enrolled. Preoperative and intraoperative factors were assessed. Each patient was evaluated for postoperative delirium 7 days after surgery. We developed machine learning models using the Bernoulli naive Bayes, Support vector machine, Random forest, Extra-trees, and XGBoost algorithms. Stratified fivefold cross-validation was performed for each developed model. Of the 87 patients, 24 (27.6%) developed postoperative delirium. Age, use of psychotropic drugs, cognitive function (Mini-Cog < 4), index of activities of daily living (Barthel Index < 100), history of stroke or cerebral hemorrhage, and eGFR (estimated glomerular filtration rate) < 60 were selected to develop delirium prediction models. The Extra-trees model had the best area under the receiver operating characteristic curve (0.76 [standard deviation 0.11]; sensitivity: 0.63; specificity: 0.78). XGBoost showed the highest sensitivity (AUROC, 0.75 [0.07]; sensitivity: 0.67; specificity: 0.79). Machine learning algorithms could predict post-cardiovascular delirium using preoperative data.Trial registration: UMIN-CTR (ID; UMIN000049390).