Virtual reality-based training may improve visual memory and some aspects of sustained attention among healthy older adults - preliminary results of a randomized controlled study.

BACKGROUND/AIMS: Older age and cognitive inactivity have been associated with cognitive impairment, which in turn is linked to economic and societal burdens due to the high costs of care, especially for care homes and informal care. Emerging non-pharmacological interventions using new technologies, such as virtual reality (VR) delivered on a head-mounted display (HMD), might offer an alternative to maintain or improve cognition. The study aimed to evaluate the efficacy and safety of a VR-based Digital Therapeutics application for improving cognitive functions among healthy older adults. METHODS: Seventy-two healthy seniors (experimental group N = 35, control group N = 37), aged 65-85 years, were recruited by the Medical University of Lodz (Poland). Participants were randomly allocated to the experimental group (a VR-based cognitive training which consists of a warm-up module and three tasks, including one-back and dual-N-back) or to the control group (a regular VR headset app only showing nature videos). The exercises are performed in different 360-degree natural environments while listening to a preferred music genre and delivered on a head-mounted display (HMD). The 12-week intervention of 12 min was delivered at least three times per week (36 sessions). Compliance and performance were followed through a web-based application. Primary outcomes included attention and working memory (CNS-Vital Signs computerized cognitive battery). Secondary outcomes comprised other cognitive domains. Mixed linear models were constructed to elucidate the difference in pre- and post-intervention measures between the experimental and control groups. RESULTS: The users performed, on average, 39.8 sessions (range 1-100), and 60% performed more than 36 sessions. The experimental group achieved higher scores in the visual memory module (B = 7.767, p = 0.011) and in the one-back continuous performance test (in terms of correct responses: B = 2.057, p = 0.003 and omission errors: B = -1.950, p = 0.007) than the control group in the post-test assessment. The results were independent of participants' sex, age, and years of education. The differences in CNS Vital Signs' global score, working memory, executive function, reaction time, processing speed, simple and complex attention, verbal memory, cognitive flexibility, motor speed, and psychomotor speed were not statistically significant. CONCLUSIONS: VR-based cognitive training may prove to be a valuable, efficacious, and well-received tool in terms of improving visual memory and some aspect of sustainability of attention among healthy older adults. This is a preliminary analysis based on part of the obtained results to that point. Final conclusions will be drawn after the analysis of the target sample size. TRIAL REGISTRATION: Clinicaltrials.gov ID NCT05369897.

A comparison study on creating simulated patient data for individuals suffering from chronic coronary disorders.

An emerging area in data science that has lately gained attention is the virtual population (VP) and synthetic data generation. This field has the potential to significantly affect the healthcare industry by providing a means to augment clinical research databases that have a shortage of subjects. The current study provides a comparative analysis of five distinct approaches for creating virtual data populations from real patient data. The data set utilized for the current analyses involved clinical data collected among patients scheduled for elective coronary artery bypass graft surgery (CABG). To that end, the five computational techniques employed to augment the given dataset were: (i) Tabular Preset, (ii) Gaussian Copula Model (iii) Generative Adversarial Network based (GAN) Deep Learning data synthesizer (CTGAN), (iv) a variation of the CTGAN Model (Copula GAN), and (v) VAE-based Deep Learning data synthesizer (TVAE). The performance of these techniques was assessed against their effectiveness in producing high-quality virtual data. For this purpose, dataset correlation matrices, cosine similarity distance, density histograms, and kernel density estimation are employed to perform a comparative analysis of each attribute and the respective synthetic equivalent. Our findings demonstrate that Gaussian Copula Model prevails in creating virtual data with consistent distributions (Kolmogorov-Smirnov (KS) and Chi-Squared (CS) tests equal to 0.9 and 0.98, respectively) and correlation patterns (average cosine similarity equals to 0.95).Clinical Relevance- It has been shown that the use of a VP can increase the predictive performance of a ML model, i.e., above using a smaller non-augmented population.

Lower Preoperative Verbal Memory Performance Is Associated with Delirium after Coronary Artery Bypass Graft Surgery: A Prospective Cohort Study.

OBJECTIVE: Cognitive impairment constitutes one of the major risk factors of delirium after coronary artery bypass graft (CABG) surgery; however, it is unclear whether only patients with global cognitive decline are at increased risk for delirium or if individuals with preserved global cognitive functions but impairments in specific cognitive domains are also more vulnerable to developing delirium. Thus, this study aimed to analyze the neurocognitive status of patients scheduled for CABG surgery with the use of an advanced computerized cognitive battery (CNS Vital Signs) and to investigate possible associations between impaired performance in selective cognitive areas and the risk of postoperative delirium development. METHODS: The study enrolled 127 participants with a median age of 67 years (IQR: 63-71). Postoperative delirium developed in 32 (25%) patients.Before surgery, the patients were screened for global cognitive impairment with the use of the Mini-Mental State Examination Test, and the individuals were asked to perform the CNS Vital Signs battery to investigate 12 specific cognitive domains. The Confusion Assessment Method and the Memorial Delirium Assessment Scale were used to screen for a diagnosis of delirium postoperatively. RESULTS: In multivariate models, a lower score of verbal memory-assessed preoperatively was independently associated with the risk of postoperative delirium development. Other independent predictors of delirium included more advanced age, gender female, depression, postoperative pyrexia, and the presence of extracorporeal circulation. CONCLUSIONS: As decreased verbal memory constitutes an independent risk factor for postoperative delirium, a verbal memory test may be a useful predictor of postoperative delirium development.

AI-Enhanced Predictive Modeling for Identifying Depression and Delirium in Cardiovascular Patients Scheduled for Cardiac Surgery.

Several studies have demonstrated a critical association between cardiovascular disease (CVD) and mental health, revealing that approximately one-third of individuals with CVD also experience depression. This comorbidity significantly increases the risk of cardiac complications and mortality, a risk that persists regardless of traditional factors. Addressing this issue, our study pioneers a straightforward, explainable, and data-driven pipeline for predicting depression in CVD patients. METHODS: Our study was conducted at a cardiac surgical intensive care unit. A total of 224 participants who were scheduled for elective coronary artery bypass graft surgery (CABG) were enrolled in the study. Prior to surgery, each patient underwent psychiatric evaluation to identify major depressive disorder (MDD) based on the DSM-5 criteria. An advanced data curation workflow was applied to eliminate outliers and inconsistencies and improve data quality. An explainable AI-empowered pipeline was developed, where sophisticated machine learning techniques, including the AdaBoost, random forest, and XGBoost algorithms, were trained and tested on the curated data based on a stratified cross-validation approach. RESULTS: Our findings identified a significant correlation between the biomarker "sRAGE" and depression (r = 0.32, p = 0.038). Among the applied models, the random forest classifier demonstrated superior accuracy in predicting depression, with notable scores in accuracy (0.62), sensitivity (0.71), specificity (0.53), and area under the curve (0.67). CONCLUSIONS: This study provides compelling evidence that depression in CVD patients, particularly those with elevated "sRAGE" levels, can be predicted with a 62% accuracy rate. Our AI-driven approach offers a promising way for early identification and intervention, potentially revolutionizing care strategies in this vulnerable population.

Increased postoperative myeloperoxidase concentration associated with low baseline antioxidant capacity as the risk factor of delirium after cardiac surgery.

BACKGROUND: Though risk factors of postoperative delirium are well described, its pathophysiology is still undiscovered. The primary objective of the current study is to assess whether increased pre- and postoperative myeloperoxidase (MPO) levels are associated with postoperative delirium in the population of cardiac surgery patients. The secondary objective is to evaluate the correlation between MPO levels and serum antioxidant capacity (AC). METHODS: The patients' cognitive status was assessed one day preoperatively with the use of the Mini-Mental State Examination Test and the Clock Drawing Test. A diagnosis of major depressive disorder and anxiety disorders was established based on DSM-5 criteria. Blood samples for MPO and AC levels were collected both pre- and postoperatively. The Confusion Assessment Method for the Intensive Care Unit was used to screen for a diagnosis of delirium. RESULTS: Delirium occurred in 34% (61 of 177) of patients. Multivariable logistic regression analysis revealed that increased postoperative MPO concentration was independently associated with postoperative delirium development, and negatively correlated with lower baseline serum AC. CONCLUSIONS: Cardiac surgery patients with less efficient antioxidative mechanisms experience a higher postoperative peak of serum MPO, which in turn may predispose to postoperative delirium development.KEY MESSAGESMPO is a lysosomal enzyme with strong pro-oxidative and pro-inflammatory properties.Cardiac surgery patients who have increased concentration of postoperative MPO are at significantly higher risk of postoperative delirium development.This higher level of postoperative MPO is negatively correlated with baseline antioxidant capacity (AC).It can be hypothesized that individuals with decreased baseline AC experience a higher peak of MPO post-surgery due to less efficient antioxidative mechanisms, which in turn contributes to postoperative delirium development.

Oxidative stress and soluble receptor for advanced glycation end-products play a role in the pathophysiology of delirium after cardiac surgery.

Coronary-artery bypass graft (CABG) surgery is known to improve cardiac function and decrease mortality, albeit, this method of treatment is also associated with a neuropsychiatric complications including postoperative delirium. The pathophysiology of delirium after cardiac surgery remains poorly understood. Thus, the purpose of this study was to investigate whether oxidative stress reflected by decreased preoperative and postoperative plasma antioxidant activity is independently associated with delirium after cardiac surgery. The second aim was to assess whether decreased antioxidant activity is stress-related or mediated by other pathologies such as major depressive disorder (MDD), anxiety disorders, and cognitive impairment. Furthermore, the putative relationship between pre- and postoperative soluble receptor for advanced glycation end-products (sRAGE) overexpression and plasma antioxidant capacity was evaluated. The patients cognitive status was assessed 1 day preoperatively with the use of the Mini-Mental State Examination Test and the Clock Drawing Test. A diagnosis of MDD and anxiety disorders was established on the basis of DSM-5 criteria. Blood samples for antioxidant capacity and sRAGE levels were collected both preoperatively and postoperatively. The Confusion Assessment Method for the Intensive Care Unit was used within the first 5 days postoperatively to screen for a diagnosis of delirium. Postoperative delirium was diagnosed in 34% (61 of 177) of individuals. Multivariate logistic regression analysis revealed that low baseline antioxidant capacity was independently associated with postoperative delirium development. Moreover, increased risk of delirium was observed among patients with a preoperative diagnosis of MDD associated with antioxidant capacity decreased postoperatively. According to receiver operating characteristic analysis, the most optimal cutoff values of the preoperative and postoperative antioxidant capacity that predict the development of delirium were 1.72 mM and 1.89 mM, respectively. Pre- and postoperative antioxidant capacity levels were negatively correlated with postoperative sRAGE concentration (Spearman's Rank Correlation - 0.198 and - 0.158, p < 0.05, respectively). Patients with decreased preoperative antioxidant activity and those with depressive episodes complicated with lower postoperative antioxidant activity are at significantly higher risk of delirium after cardiac surgery development. sRAGE overexpression may be considered as protective mechanism against increased oxidative stress and subsequent cell damage.