Search Results (1,132)

In recent years, data augmentation techniques have become the predominant approach for addressing highly imbalanced classification problems in machine learning. Algorithms such as the Synthetic Minority Over-sampling Technique (SMOTE) and Conditional Tabular Generative Adversarial Network (CTGAN) have proven effective in synthesizing minority class samples. However, these methods often introduce distributional bias and noise, potentially leading to model overfitting, reduced predictive performance, increased computational costs, and elevated cybersecurity risks. To overcome these limitations, we propose a novel architecture, FADEL, which integrates feature-type awareness with a supervised discretization strategy. FADEL introduces a unique feature augmentation ensemble framework that preserves the original data distribution by concurrently processing continuous and discretized features. It dynamically routes these feature sets to their most compatible base models, thereby improving minority class recognition without the need for data-level balancing or augmentation techniques. Experimental results demonstrate that FADEL, solely leveraging feature augmentation without any data augmentation, achieves a recall of 90.8% and a G-mean of 94.5% on the internal test set from Kaohsiung Chang Gung Memorial Hospital in Taiwan. On the external validation set from Kaohsiung Medical University Chung-Ho Memorial Hospital, it maintains a recall of 91.9% and a G-mean of 86.7%. These results outperform conventional ensemble methods trained on CTGAN-balanced datasets, confirming the superior stability, computational efficiency, and cross-institutional generalizability of the FADEL architecture. Altogether, FADEL uses feature augmentation to offer a robust and practical solution to extreme class imbalance, outperforming mainstream data augmentation-based approaches. Full article

p-Cresyl sulfate (PCS), a gut-derived uremic toxin with proinflammatory and cytotoxic effects, has been implicated in cardiovascular injuries among patients with chronic kidney disease (CKD). Aortic stiffness (AS), assessed by carotid–femoral pulse wave velocity (cfPWV), is a recognized predictor of cardiovascular risk. This study investigated the association between serum PCS levels and AS in patients with nondialysis-dependent CKD. In total, 165 patients with nondialysis-dependent CKD were enrolled. Clinical data and fasting blood samples were collected. Arterial stiffness (AS) was assessed bilaterally by measuring carotid–femoral pulse wave velocity (cfPWV) on both the left and right sides. A value above 10 m/s was considered indicative of increased stiffness. Serum PCS levels were quantified using high-performance liquid chromatography–mass spectrometry. Fifty patients (30.3%) had AS. The AS group was significantly older and had higher diabetes prevalence, systolic blood pressure, fasting glucose, urinary protein-creatinine ratio, and PCS levels than the control group. In the multivariate analysis, both PCS (odds ratio [OR]: 1.097; 95% confidence interval [CI]: 1.024–1.175; p = 0.008) and age (OR: 1.057; 95% CI: 1.025–1.090; p < 0.001) were independently associated with AS. In conclusion, elevated serum PCS and older age were independently associated with AS. Thus, PCS is a potential early marker of vascular damage in CKD. Full article

Aminoglycoside antibiotics are critical in clinical use for treating severe infections, but they can occasionally cause irreversible sensorineural hearing loss. To establish a rational pathway for otoprotectant discovery, we provide an integrated, three-tier methodology—comprising cell-model selection, transcriptomic analysis, and a gentamicin–Texas Red (GTTR) uptake assay—to guide the development of otoprotective strategies. We first utilized two murine auditory cell lines—UB/OC-2 and HEI-OC1. We focused on TMC1 and OCT2 and further explored the underlying mechanisms of ototoxicity. UB/OC-2 exhibited a higher sensitivity to gentamicin, which correlated with elevated OCT2 expression confirmed via RT-PCR and Western blot. Transcriptomic analysis revealed upregulation of PI3K-Akt, calcium, and GPCR-related stress pathways in gentamicin-treated HEI-OC1 cells. Protein-level analysis further confirmed that gentamicin suppressed phosphorylated Akt while upregulating ER stress markers (GRP78, CHOP) and apoptotic proteins (cleaved caspase 3, PARP). Co-treatment with PI3K inhibitors (LY294002, wortmannin) further suppressed Akt phosphorylation, supporting the role of PI3K-Akt signaling in auditory cells. To visualize drug entry, we used GTTR to evaluate its applicability as a fluorescence-based uptake assay in these cell lines, which were previously employed mainly in cochlear explants. Sodium thiosulfate (STS) and N-acetylcysteine (NAC) significantly decreased GTTR uptake, suggesting a protective effect against gentamicin-induced hair cell damage. In conclusion, our findings showed a complex ototoxic cascade involving OCT2- and TMC1-mediated drug uptake, calcium imbalance, ER stress, and disruption of PI3K-Akt survival signaling. We believe that UB/OC-2 cells serve as a practical in vitro model for mechanistic investigations and screening of otoprotective compounds. Additionally, GTTR may be a simple, effective method for evaluating protective interventions in auditory cell lines. Overall, this study provides molecular-level insights into aminoglycoside-induced ototoxicity and introduces a platform for protective strategies. Full article

Kawasaki disease (KD) is a rare yet potentially life-threatening pediatric vasculitis that, if left undiagnosed or untreated, can result in serious cardiovascular complications. Its heterogeneous clinical presentation poses diagnostic challenges, often failing to meet classical criteria and increasing the risk of oversight. Leveraging routine laboratory tests with AI offers a promising strategy for enhancing early detection. However, due to the extremely low prevalence of KD, conventional models often struggle with severe class imbalance, limiting their ability to achieve both high sensitivity and specificity in practice. To address this issue, we propose a multi-stage AI-based predictive framework that incorporates clustering-based undersampling, data augmentation, and stacking ensemble learning. The model was trained and internally tested on clinical blood and urine test data from Chang Gung Memorial Hospital (CGMH, n = 74,641; 2010–2019), and externally validated using an independent dataset from Kaohsiung Medical University Hospital (KMUH, n = 1582; 2012–2020), thereby supporting cross-institutional generalizability. At a fixed recall rate of 95%, the model achieved a specificity of 97.5% and an F1-score of 53.6% on the CGMH test set, and a specificity of 74.7% with an F1-score of 23.4% on the KMUH validation set. These results underscore the model’s ability to maintain high specificity even under sensitivity-focused constraints, while still delivering clinically meaningful predictive performance. This balance of sensitivity and specificity highlights the framework’s practical utility for real-world KD screening. Full article

Monitoring fetal growth throughout pregnancy is essential for early detection of developmental abnormalities. This study developed a Taiwan-specific fetal growth reference using a web-based data collection platform and polynomial regression modeling. We analyzed ultrasound data from 980 pregnant women, encompassing 8350 prenatal scans, to model six key fetal biometric parameters: abdominal circumference, crown–rump length, estimated fetal weight, head circumference, biparietal diameter, and femur length. Quadratic regression was selected based on a balance of performance and simplicity, with R² values exceeding 0.95 for most parameters. Confidence intervals and real-time anomaly detection were implemented through the platform. The results demonstrate the potential for efficient, population-specific fetal growth monitoring in clinical settings. Full article

To correspond to the advancement of technology, programming has become an indispensable course in university curricula. However, students easily become confused by the rules governing program execution or by complex logical structures. Mastering program structure and logic often is a significant challenge for beginners, especially. Despite the availability of information on programming on various websites and tools, including generative artificial intelligence (AI), there is still a gap between conceptual understanding and practical application for beginners. They overlook important implementation details or struggle to grasp the flow of a program, making the mastery of program logic a persistent challenge. To address these issues, we have developed a system that dynamically generates process architecture diagrams. Users upload their code, and the system produces corresponding diagrams that decompose and execute the code line by line. Its visual representation allows users to observe the program’s execution and aids them in comprehending the sequence and operational flow of the code. By understanding the structure and logic of the program intuitively, this system supplements traditional teaching methods and AI-assisted question-and-answer tools. The experimental results demonstrated that students found the system helpful to track their learning progress (87%) and improved their understanding of program code (81%). Additionally, 84% of students reported that the system was easy to use, highlighting its user-friendliness. In terms of student interest, 83% of students agreed that the interactive elements made learning more engaging, indicating that the system positively contributed to dynamic and enjoyable learning. However, 63% of students reported an improvement in coding and were influenced by the complexity of the programming tasks assigned. Despite this, the overall satisfaction with the system developed in this study was high. Full article

Transcriptomic profiling has shown that exposure to PM_2.5, a common air pollutant, can modulate gene expression, which has been linked to negative health effects and diseases. However, there are few population-based cohort studies on the association between PM_2.5 exposure and specific gene set expression. In this study, we used an unbiased transcriptomic profiling approach to examine gene expression in a mouse model exposed to PM_2.5 and to identify PM_2.5-responsive genes. The gene expressions were further validated in both the human cell lines and a population-based cohort study. Two cohorts of healthy older adults (aged ≥ 65 years) were recruited from regions characterized by differing levels of PM_2.5. Logistic regression and decision tree algorithms were then utilized to construct predictive models for PM_2.5 exposure based on these gene expression profiles. Our results indicated that the expression of five genes (FAM102B, PPP2R1B, OXR1, ITGAM, and PRP38B) increased with PM_2.5 exposure in both cell-based assay and population-based cohort studies. Furthermore, the predictive models demonstrated high accuracy in classifying high-and-low PM_2.5 exposure, potentially supporting the integration of gene biomarkers into public health practices. Full article

Dengue virus (DENV) infection is strongly associated with dengue hemorrhagic fever and dengue shock syndrome, both of which carry mortality risks. Addressing the urgent need for effective dengue therapeutics, we identified sofalcone, a gastroprotective agent with antioxidant and anti-inflammatory properties, as a potential inhibitor of DENV replication. Sofalcone demonstrated efficacy against all four DENV serotypes, with the dose inhibiting 50% (IC50) value of 28.1 ± 0.42 μM against viral replication of DENV serotype 2, without significant cytotoxicity. Additionally, sofalcone significantly improved survival rates and reduced viral titers in DENV-infected ICR-suckling mice. Mechanistically, sofalcone induced heme oxygenase-1 (HO-1) expression via the nuclear factor-erythroid 2-reated factor 2 (Nrf2) pathway, which in turn suppressed viral protease activity and restored antiviral interferon (IFN) responses. This included dose-dependent stimulation of IFN downstream antiviral genes such as 2′-5′-oligoadenylate synthetase 1 (OAS1), OAS2, and OAS3. Given its established clinical use as an anti-gastric ulcer drug, sofalcone offers promising potential for rapid application in treating DENV infection. Full article

The spindle is a critical component that significantly influences the performance of machine tools. In motorized spindles, heat generation from both the bearings and built-in motor leads to thermal deformation of structural components, which, in turn, affects machining accuracy. This study investigates the thermo-mechanical behavior of motorized spindles under various operational conditions, with the aim of accurately predicting thermally induced axial deformation and determining optimal temperature sensor placement. To achieve this, temperature rise and deformation data were simultaneously collected using appropriate data acquisition systems across varying spindle speeds. A correlation analysis confirmed a strong positive relationship exceeding 97.5% between temperature rise at all sensor locations and axial thermal deformation. Multivariate regression analysis was then applied to identify optimal combinations of sensor data for accurate deformation prediction. Additionally, a finite element (FE) thermal–mechanical model was developed to simulate spindle behavior, with the results validated against experimental measurements and regression model predictions. The four-variable regression model and FE simulation achieved Root Mean Square Errors (RMSEs) of 0.84 µm and 0.82 µm, respectively, both demonstrating close agreement with experimental data and effectively capturing the trend of thermal deformation over time under different operating conditions. Finally, an optimal sensor configuration was identified that minimizes pre-diction error while reducing the number of required sensors. Overall, the proposed methodology offers valuable insights for optimizing spindle design to enhance thermal–mechanical performance. Full article

Indoxyl sulfate (IS), which is a protein-bound uremic toxin, is involved in vascular dysfunction and cardiovascular risk in subjects with chronic kidney disease (CKD). However, its role in peripheral arterial stiffness (PAS) remains unclear. This cross-sectional study evaluated the relationship between IS and PAS in patients diagnosed with CKD stages 3 through 5 who are not undergoing dialysis. Patients with CKD from a single center were enrolled. High-performance liquid chromatography analyzed the serum IS levels. PAS was evaluated using brachial–ankle pulse wave velocity (baPWV). IS was independently associated with PAS (odds ratio [OR]: 1.389 for 1 μg/mL increase in IS, 95% confidence interval [CI]: 1.086–1.775, p = 0.009) in a multivariable analysis after adjustment for age, hypertension, diabetes mellitus, blood pressure, lipid profiles, renal function, albumin, and proteinuria. Moreover, the mean baPWV (p = 0.010), left baPWV (p = 0.009), and right baPWV (p = 0.015) levels significantly correlated with the log-transformed IS (log-IS) levels. The area under the receiver operating characteristic curve for serum IS as a predictor of PAS was determined to be 0.667 (95% CI: 0.580−0.754; p = 0.0002). IS was associated with PAS in non-dialysis CKD stages 3–5, suggesting that IS may be a possible vascular risk marker. Future studies should address the nature of the relationship between IS and vascular dysfunction and assess therapeutic strategies to reduce IS. Full article

Background: Intra-abdominal infections (IAIs) caused by Stenotrophomonas maltophilia have rarely been reported. This study aimed to describe the clinical characteristics and risk factors for mortality among patients with S. maltophilia IAIs. Methods: A retrospective study was conducted on inpatients with IAIs caused by S. maltophilia at Tri Service General Hospital from 2004 to 2017. Clinical and microbiologic data of the included cases were reviewed via medical charts and microbiology databases. Multivariable logistic regression analyses were performed to identify risk factors for in-hospital death. Results: In total, 110 patients were diagnosed with S. maltophilia IAIs. Malignancy (56.3%) and liver cirrhosis (35.3%) were the most commonly identified underlying diseases. The major causes of S. maltophilia IAIs were biliary tract infection (42.7%), recent abdominal surgery (35.4%), and spontaneous bacterial peritonitis (20.0%). Polymicrobial infections were observed in 84 (76.4%) patients. In addition to S. maltophilia, co-cultured bacteria (n = 140) included Enterobacterales, representing 19.3% (27/140) of the total isolates, and non-fermentative aerobes, comprising 29.3% (41/140). In addition, anaerobic bacteria and fungi accounted for 9.2% (13/140) and 10% (14/140), respectively. The overall mortality rate was 40.9%. Multivariable logistic regression analysis revealed that high Sequential Organ Failure Assessment scores and malignancies were independent risk factors for mortality, while the immediate administration of appropriate antibiotics targeting S. maltophilia was a protective factor (p < 0.05). Conclusions: Patients with an underlying malignancy or liver cirrhosis were at risk for IAIs caused by S. maltophilia. The prompt initiation of effective antibiotics against S. maltophilia is critical for achieving favorable outcomes. Full article

The marine ornamental species trade relies heavily on wild-caught specimens, including the Vermiculated angelfish (Chaetodontoplus mesoleucus). Captive breeding of this species faces challenges with limited detailed knowledge available beyond 2 days post-hatch (dph) regarding the influence of environmental factors. This study provides a detailed characterization of C. mesoleucus from early development to 381 dph. Under controlled laboratory conditions, the effect of temperature (22–37 °C) on hatching rate, deformity rate, hatching period duration, time to 50% hatch, and survival rate is investigated. Additionally, the influence of different salinities (0–38 psu) on hatching rates and larval deformity rates was also examined. The optimal incubation temperatures for high hatching rate and minimal larval deformities are found to be within 25–28 °C. A lower salinity threshold of 10 psu was established for successful hatching, and the optimal salinity range for minimizing larval deformities was 33–36 psu. These findings provide crucial baseline data and practical recommendations for optimizing hatchery protocols for C. mesoleucus, contributing to enhanced larval survival and the potential for sustainable aquaculture production, thereby reducing the pressure on wild populations. Full article

Hepatitis C virus (HCV) infection remains a significant global health burden, driven by the emergence of drug-resistant strains and the limited efficacy of current antiviral therapies. A promising strategy for therapeutic intervention involves targeting the NS3 protease, a viral enzyme essential for replication. In this study, we present the first computational model specifically designed to identify NS3 protease inhibitory peptides (NS3IPs). Using amino acid composition (AAC) and K-spaced amino acid pair composition (CKSAAP) features, we developed machine learning classifiers based on support vector machine (SVM) and random forest (RF), achieving accuracies of 98.85% and 97.83%, respectively, validated through 5-fold cross-validation and independent testing. To support the accessibility of the strategy, we implemented a web-based tool, iDNS3IP, which enables real-time prediction of NS3IPs. In addition, we performed feature space analyses using PCA, t-SNE, and LDA based on AAindex descriptors. The resulting visualizations showed a distinguishable clustering between NS3IPs and non-inhibitory peptides, suggesting that inhibitory activity may correlate with characteristic physicochemical patterns. This study provides a reliable and interpretable platform to assist in the discovery of therapeutic peptides and supports continued research into peptide-based antiviral strategies for drug-resistant HCV. To enhance its flexibility, the iDNS3IP web tool also incorporates a BLAST-based similarity search function, enabling users to evaluate inhibitory candidates from both predictive and homology-based perspectives. Full article

Background/Objectives: Poor sleep quality is a prevalent health concern among older adults, impacting cognitive and physical functions. This study aimed to determine the association between sleep quality and self-reported health status among middle-aged and older adults in northern Taiwan. Methods: This cross-sectional study, conducted from April to October 2017, assessed participants using the Chinese version of the Pittsburgh Sleep Quality Index (CPSQI) with a cut-off of 5; scores above 5 indicated poor sleep quality. The self-reported health status was evaluated using a questionnaire. Statistical analyses included the chi-squared test, one-way ANOVA, Cochran–Armitage trend test, and multiple logistic regression models. Results: This study included 850 adults (243 males and 607 females). The participants were grouped according to their self-reported health status as follows: good (n = 278), fair (n = 499), and poor (n = 73). Poor health status was associated with worse sleep quality components, including sleep latency, efficiency, disturbances, medication use, and daytime dysfunction (p for trend < 0.001). The multiple logistic regression analysis showed higher dissatisfaction with health status among the participants with a CPSQI score of >5 (odds ratio, 4.12; 95% CI 2.26–7.50; p < 0.001). A poor health status was reported by 19.51% of the participants sleeping < 5 h, compared to 6.97% of the participants sleeping 5–6 h, 6.60% of the participants sleeping 6–7 h, and 6.34% of the participants sleeping > 7 h, showing a trend toward a shorter sleep duration (p for trend = 0.002). Conclusions: Our study findings indicate that a poor sleep quality and short sleep duration were independent risk factors for poor self-reported health status in middle-aged and older adults in Taiwan. Addressing sleep quality is crucial for implementing preventive health measures in this demographic group. Full article

Nowadays, underwater activities are becoming more and more important. As the number of underwater sensing devices grows rapidly, the amount of bandwidth needed also increases very quickly. Apart from underwater communication, direct communication across the water–air interface is also highly desirable. Air-to-water wireless transmission is crucial for sending control information or instructions from unmanned aerial vehicles (UAVs) or ground stations above the sea surface to autonomous underwater vehicles (AUVs). On the other hand, water-to-air wireless transmission is also required to transmit real-time information from AUVs or underwater sensor nodes to UAVs above the water surface. Previously, we successfully demonstrated a water-to-air optical camera-based OWC system, which is also known as optical camera communication (OCC). However, the reverse transmission (i.e., air-to-water) using OCC has not been analyzed. It is worth noting that in the water-to-air OCC system, since the camera is located in the air, the image of the light source is magnified due to diffraction. Hence, the pixel-per-symbol (PPS) decoding of the OCC pattern is easier. In the proposed air-to-water OCC system reported here, since the camera is located in the water, the image of the light source in the air will be diminished in size due to diffraction. Hence, the PPS decoding of the OCC pattern becomes more difficult. In this work, we propose and experimentally demonstrate a wide field-of-view (FOV) air-to-water OCC system using CUDA Deep-Neural-Network Long-Short-Term-Memory (CuDNNLSTM). Due to water turbulence and air turbulence affecting the AUV and UAV, a precise line-of-sight (LOS) between the AUV and the UAV is difficult to achieve. OCC can provide wide FOV without the need for precise optical alignment. Results revealed that the proposed air-to-water OCC system can support a transmission rate of 7.2 kbit/s through a still water surface, and 6.6 kbit/s through a wavy water surface; this satisfies the hard-decision forward error correction (HD-FEC) bit-error-rate (BER). Full article