What is the impact of perioperative cerebral oxygen desaturation on postoperative delirium in old population: a systemic review and meta-analysis

Machine learning with clinical and intraoperative biosignal data for predicting postoperative delirium after cardiac surgery

Early identification of patients at high risk of delirium is crucial for its prevention. Our study aimed to develop machine learning models to predict delirium after cardiac surgery using intraoperative biosignals and clinical data. We introduced a novel approach to extract relevant features from continuously measured intraoperative biosignals. These features reflect the patient's overall or baseline status, the extent of unfavorable conditions encountered intraoperatively, and beat-to-beat variability within the data. We developed a soft voting ensemble machine learning model using retrospective data from 1,912 patients. The model was then prospectively validated with data from 202 additional patients, achieving a high performance with an area under the receiver operating characteristic curve of 0.887 and an accuracy of 0.881. According to the SHapley Additive exPlanation method, several intraoperative biosignal features had high feature importance, suggesting that intraoperative patient management plays a crucial role in preventing delirium after cardiac surgery.

Associations of body mass index with severe outcomes of COVID-19 among critically ill elderly patients: A prospective study

Background and Aim

Few studies assessed the associations of overweight and obesity with severe outcomes of coronavirus disease 2019 (COVID-19) among elderly patients. This study was conducted to assess overweight and obesity in relation to risk of mortality, delirium, invasive mechanical ventilation (IMV) requirement during treatment, re-hospitalization, prolonged hospitalization, and ICU admission among elderly patients with COVID-19.

Methods

This was a single-center prospective study that was done on 310 elderly patients with COVID-19 hospitalized in the intensive care unit (ICU). We collected data on demographic characteristics, laboratory parameters, nutritional status, blood pressure, comorbidities, medications, and types of mechanical ventilation at baseline. Patients were followed up during ICU admission and until 45 days after the first visit, and data on delirium incidence, mortality, need for a form of mechanical ventilation, discharge day from ICU and hospital, and re-hospitalization were recorded for each patient.

Results

During the follow-up period, we recorded 190 deaths, 217 cases of delirium, and 35 patients who required IMV during treatment. After controlling for potential confounders, a significant association was found between obesity and delirium such that obese patients with COVID-19 had a 62% higher risk of delirium compared with normal-weight patients (HR: 1.62, 95% CI: 1.02-2.57). This association was not observed for overweight. In terms of other outcomes including ICU/45-day mortality, IMV therapy during treatment, re-hospitalization, prolonged hospitalization, and ICU admission, we found no significant association with overweight and obesity either before or after controlling for potential confounders.

Conclusion

We found that obesity may be a risk factor for delirium among critically ill elderly patients with COVID-19.