Journal of clinical medicine
-
Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. ⋯ In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.
-
Heart rate variability (HRV) as an accurate, noninvasive measure of the Autonomous Nervous System (ANS) can reflect mental health (e.g., stress, depression, or anxiety). Tai Chi and Yoga (Tai Chi/Yoga), as the most widely practiced mind⁻body exercises, have shown positive outcomes of mental health. To date, no systematic review regarding the long-lasting effects of Tai Chi/Yoga on HRV parameters and perceived stress has been conducted. ⋯ Stress reduction may be attributed to sympathetic-vagal balance modulated by mind⁻body exercises. Tai Chi/Yoga could be an alternative method for stress reduction for people who live under high stress or negative emotions.
-
The purpose of this study was to compare the incidence of airway complications between extubation under deep anesthesia (deep extubation) and extubation when fully awake (awake extubation) in pediatric patients after general anesthesia. A systematic review was performed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) statement standards. The review protocol was registered with the International Prospective Register of Systematic Reviews (registration number: CRD 42018090172). ⋯ No difference was observed in the incidence of laryngospasm and breath-holding between the two groups regardless of airway device. The result of this analysis indicates that deep extubation may decrease the risk of overall airway complications including cough and desaturation but may increase airway obstruction compared with awake extubation in pediatric patients after general anesthesia. Therefore, deep extubation may be recommended in pediatric patients to minimize overall airway complications except airway obstruction and the clinicians may choose the method of extubation according to the risk of airway complications of pediatric patients.
-
Opioid consumption has increased worldwide, which carries the risk of opioid use disorder (OUD). However, the literature on OUD and opioid-related chemical coping (OrCC) in chronic noncancer pain (CNCP) is heterogeneous, with most studies conducted in the United States. We performed a multicenter, observational, cross-sectional study to address OrCC in long-term opioid therapy (LtOT) for CNCP in South Korea. ⋯ OrCC patients had greater pain interference (85.18% vs. 58.28%, p = 0.017) and lower satisfaction with the LtOT (56.4% vs. 78.3%, p = 0.002). In multivariable analysis, alcohol abuse (OR = 6.84, p = 0.001), prescription drugs abuse (OR = 19.32, p = 0.016), functional pain (OR = 12.96, p < 0.001), head and neck pain (OR = 2.48, p = 0.039), MEDD (morphine equivalent daily dose) ≥ 200 mg/day (OR = 3.48, p = 0.006), and ongoing litigation (OR = 2.33, p = 0.047) were significant predictors of OrCC. In conclusion, the break-out of OrCC in CNCP in South Korea was comparable to those in countries with high opioid consumption, such as the United States, regardless of the country's opioid consumption rate.
-
Machine learning approaches were introduced for better or comparable predictive ability than statistical analysis to predict postoperative outcomes. We sought to compare the performance of machine learning approaches with that of logistic regression analysis to predict acute kidney injury after cardiac surgery. We retrospectively reviewed 2010 patients who underwent open heart surgery and thoracic aortic surgery. ⋯ Decision tree, random forest, and support vector machine showed similar performance to logistic regression. In our comprehensive comparison of machine learning approaches with logistic regression analysis, gradient boosting technique showed the best performance with the highest AUC and lower error rate. We developed an Internet⁻based risk estimator which could be used for real-time processing of patient data to estimate the risk of AKI at the end of surgery.