Wind energy conversion systems (WECSs) play a vital role in the transition to sustainable energy, requiring continuous advancements in reliability, efficiency, and predictive maintenance. This paper provides a comprehensive review of Bayesian Networks (BNs) as a robust probabilistic framework for enhancing fault detection, risk assessment, and condition monitoring in WECSs. By integrating diverse data sources—including supervisory control and data acquisition (SCADA) systems, sensor networks, and environmental monitoring tools—BNs facilitate predictive maintenance, improve failure diagnostics, and extend turbine lifespan through adaptive learning. Their capability to quantify uncertainty and model complex dependencies makes them particularly effective in addressing operational and failure uncertainties, ensuring reliable energy generation under variable environmental conditions. The paper further examines key implementation challenges, including computational demands, data integration complexities, and the need for high-quality datasets to refine probabilistic models. Future research directions focus on hybridizing BNs with deep learning (DL) and reinforcement learning (RL), incorporating real-time sensor data for adaptive reliability analysis, and developing scalable, computationally efficient frameworks. Given the rapid advancements in machine learning and data-driven methodologies over the past five years, this review highlights the evolving role of BNs in modernizing WECS operations, emphasizing the necessity of an updated perspective to address emerging challenges and opportunities in wind energy systems.

Syphilis and other sexually transmitted infections (STIs) are highly prevalent in most regions experiencing severe human immunodeficiency virus (HIV) epidemics. In sub-Saharan Africa, the region most heavily affected by HIV, the prevalence of syphilis among people living with HIV (PLWH) is notably high. This region accounts for 40% of global STIs and 70% of HIV cases. Despite the high prevalence of syphilis and other STIs among PLWH in the region, there are limited studies on the interplay between the two infections from the region. Most studies on the association between syphilis and HIV transmission/progression from the region are limited to specific groups of people, such as female sex workers or pregnant women. In this manuscript, we evaluated the association between the two infections using population-based surveys conducted in the region. Statistical methods (such as logistic regression models and propensity score matching) were employed to assess the interplay between the two infections. Our findings indicated that syphilis infection was associated with higher odds of HIV acquisition. Moreover, co-infection with syphilis was associated with higher odds of HIV disease progression among antiretroviral therapy (ART)-treated PLWH, though the association did not reach statistical significance. Our findings suggest that the recognition and treatment of syphilis to reduce the risk of HIV acquisition/progression should be a public health priority in sub-Saharan Africa, where ART may not be readily available.

Extrahepatic Cholangiocarcinoma (eCCA) is one of the most severe cancers, owing to ineffective therapeutics and resistance to treatments. There has been a lack of knowledge on the pathogenesis of eCCA, which necessitates the investigation of fine biomarkers and the discovery of targeted therapies. Bayesian networks (BNs) are known as impactful tools for dissecting gene-gene interaction in complex biological networks. Initially, we identified differentially expressed genes in eCCA using the GSE132305 dataset from GEO. eCCA-related genes were obtained separately from DisGeNET. The overlap of these two gene sets resulted in a robust minimal gene list with known roles in eCCA. We then proceeded to select the highest up-and down-regulated genes to combine them with the overlapped genes. This led us to the final dataset which was later used as the input for “bnlearn” R package to generate BNs. Investigation of the generated BNs, led to the detection of candidate genes being connected to the parent nodes, namely APOC1, PIGR, FOSB, RPS6, FGA, CTSE, and ITIH2. Further literature review revealed that out of seven candidate genes, only two (FOSB and FGA) had been reported previously in the context of cholangiocarcinoma. The other five (APOC1, PIGR, RPS6, CTSE and ITIH2) have not been reported to have any roles in eCCA. Our results can potentially be the foundation for designing new studies on the mentioned genes to delve into the molecular mechanism behind the pathogenesis of eCCA and the discovery of novel drug targets. This study emphasizes the power of BNs combined with bioinformatics tools to unlock new avenues in the understanding and treatment of complex diseases such as eCCA.

BACKGROUND: Early-life vascular risk factors are increasingly linked to midlife cognitive decline, though critical risk periods remain unclear. These factors also relate to structural brain changes, yet midlife alterations tied to cognitive decline are poorly defined. We leveraged data from the CARDIA study (Coronary Artery Risk Development in Young Adults) to identify critical periods and factors associated with midlife cognition and neuroimaging signatures. METHODS: We utilized longitudinal cognitive and neuroimaging data from the prospective CARDIA study with vascular risk factor data spanning 35 years (1985–2020). K-means clustering of cognitive trajectories identified Declined and Stable clusters. A gradient boosting classifier identified factors predictive of cluster membership. Linear mixed-effects models assessed cluster differences in structural brain changes, and structural covariance analyses identified brain network remodeling linked to cognitive decline. Cross-sectional late-midlife cognitive data were used to examine associations between early adulthood (ages 18–40 years) systolic blood pressure strata and cognitive outcomes. RESULTS: Among 280 participants with longitudinal data (mean age, 50±3.5 years at baseline; 52% to 56% female, 40% to 41% Black race) followed for a median of 10 years, higher systolic blood pressure and smoking before age 40 years were critical factors for cognitive cluster membership in late midlife (feature importance ≈0.3 and 0.2, respectively). Accelerated accumulation of white matter hyperintensities, gray matter volume changes involving frontal and temporal association cortices, occipital pole and thalamus (β range, –0.0006 to –0.002; P ≤0.02), and network-level reorganization predominantly involving the basal forebrain spanning early- to late-midlife distinguished clusters. A stepwise, dose-dependent association between early-life systolic blood pressure strata and late-midlife cognitive performance was replicated in 720 participants (mean age, 61±3.5 years). CONCLUSIONS: Before age 40 years may be a critical window to manage vascular risk factors and preserve midlife cognition. Linked white matter hyperintensity and gray matter changes suggest that vascular factors drive both cerebrovascular and neurodegenerative injury. A basal forebrain–centered neuroimaging signature, possibly reflecting cholinergic and glial responses to early vascular stress, may serve as an early biomarker for prevention trials.

In the digital era, cloud-based video transcoding services are essential for platforms like Netflix and YouTube, relying on virtual machines for efficient processing. While prior research has primarily explored performance evaluation, limited attention has been given to the resilience of these services against emerging disruptions. This paper aims to predict the processing rate of video transcoding services to evaluate the resilience of small, medium, and large VMs within a cloud environment by applying four regression models. Findings reveal that a mixed regression model incorporating covariates, their interactions, and polynomial terms provides the most accurate prediction of performance and resilience. Among the VMs, the small VM exhibits the highest resilience, sustaining robust performance across varying conditions, with mean time to failure identified as the key factor in its sustained operation. These insights underscore the significance of predictive models for forecasting resilience, supporting proactive decisions for preventive maintenance and fault-tolerant design to reduce cloud service downtime.