Search Results (2,904)

Rapid and non-destructive identification of oilseed rape varieties and prediction of leaf Soil Plant Analysis Development (SPAD) value and water content are important for variety evaluation and plant-status monitoring. However, hyperspectral prediction is constrained by small sample size, costly reference measurements, and acquisition-batch differences. Samples were collected over four consecutive days. Day 1 samples were used for training and Wasserstein generative adversarial network with gradient penalty (WGAN-GP) generation. For Days 2–4, 20% of the samples from each day were combined to form a selection-validation set, while the remaining 80% were retained separately as Test sets 1–3. The improved WGAN-GP integrated principal component analysis–Gaussian mixture model (PCA–GMM)-based class assignment, a partial least squares regression (PLSR) consistency loss, physicochemical distribution control, and generated-sample selection. Under single-task modeling, the improved framework enhanced all three tasks across the test sets. On Test set 3, variety accuracy increased from 0.4672 to 0.6100, SPAD root mean square error of prediction (RMSEP) decreased from 6.2201 to 4.6303, and the water-content test-set correlation coefficient (r_p) increased from 0.6803 to 0.7842. The improved multi-task model also enhanced all three tasks. These findings support the framework within the investigated three-variety, four-day leaf setting. Full article

Early identification of individuals with abnormal glucose metabolism is essential for timely intervention and prevention of diabetes-related complications. Routine laboratory testing generates large amounts of clinical data that may support automated glycemic classification through machine learning approaches. This study aimed to develop and evaluate a machine learning framework for the classification of HbA1c-defined glycemic status using routinely available clinical laboratory features. A retrospective dataset of 1434 individuals with available glycemic measurements was analyzed. Participants were categorized into HbA1c-defined normoglycemic, prediabetic-range, or diabetic-range groups. Three concurrent classification tasks were examined: HbA1c-defined dysglycemia classification, diabetic-range HbA1c classification, and multiclass HbA1c-defined glycemic-status classification. Demographic, biochemical, and hematological variables were used as predictors. Data preprocessing included missing-value handling, feature filtering, and outlier treatment. Several supervised learning algorithms were evaluated, including Logistic Regression, Random Forest, Gradient Boosting, Support Vector Machine, and Multinomial Logistic Regression. Model performance was assessed using train–test validation and cross-validation with accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve. For dysglycemia, Gradient Boosting achieved the highest AUC (0.848), while Random Forest achieved the highest accuracy (0.801) and sensitivity (0.908). For diabetic-range HbA1c, Random Forest achieved the highest AUC (0.864), whereas SVM achieved the highest accuracy (0.794). In multiclass classification, Random Forest achieved the highest accuracy (0.610), while Gradient Boosting achieved the highest macro-AUC (0.796) and macro-F1 score (0.603). Pairwise comparisons showed no statistically significant superiority of any classifier after Holm correction. Clinical-baseline and ablation analyses demonstrated that fasting glucose accounted for a substantial proportion of discrimination, with only modest incremental value from additional laboratory variables. These findings support cautious interpretation of routine laboratory-based classification models pending further validation and clinical-utility assessment. Full article

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) affects an estimated 6% of adults in the United States and contributes to a significant economic burden. Telehealth has emerged as a vital tool in the management of ADHD, offering improved access to care, especially for individuals in underserved communities. Despite its growing role, there remain critical gaps in understanding how social determinants of health (SDOH) are associated with disparities in telehealth utilization for ADHD treatment. Objectives and Methods: This study analyzed data from the National Center for Health Statistics (NCHS) Rapid Surveys System (RSS) Round 2: ADHD (October–November 2023), a nationally fielded survey of U.S. adults. Respondents were classified into three groups: never diagnosed, previously diagnosed, and currently diagnosed with ADHD. The study aimed to (1) compare the distribution of SDOH across ADHD status groups and the general adult population to identify factors associated with ADHD diagnosis; (2) assess the homogeneity of SDOH distributions across ADHD groups; (3) evaluate telehealth utilization among adults currently diagnosed with ADHD; and (4) examine the relationship between SDOH and telehealth use for ADHD treatment. Multivariable logistic regression (MVLR) served as a benchmark model, while machine learning (ML) models—including regularized linear regression, support vector machine (SVM), random forest (RF), LightGBM, multilayer perceptron (MLP), and Few-Shot Learning (FSL)—were trained to identify key predictors. Results: A total of 7009 survey responses were analyzed: 124 had a past diagnosis, 444 were currently diagnosed, and the remainder had never been diagnosed with ADHD, corresponding to a current ADHD prevalence of 6.3%. Adults with current ADHD were more likely to be male, single, younger, white, non-homeowners, and frequent users of online health resources. They also reported lower education, income, and financial security. About 70% used telehealth for counseling and prescriptions; insurance covered telehealth visits for 82.32% of users, yet 38.76% reported no coverage of ADHD-related diagnostic or treatment costs. Nineteen SDOH elements across four domains—demographic, socioeconomic, neighborhood/built environment, and healthcare access—were identified as predictors. ML models outperformed MVLR, with SVM and FSL achieving the highest F1 (both 0.63), and FSL the highest recall (0.69). Age, race, marital status, difficulty paying bills, home ownership, education, and household size were the most consistently important variables. Limitations: This study is limited by a cross-sectional design, reliance on self-reported ADHD diagnoses, and a lack of genetic or family-history measures. Additionally, the omission of complex sampling weights limits the national representativeness of these findings. Finally, the small effective sample size poses risks of model overfitting, and the generalizability of the models could not be externally validated due to the unavailability of comparable independent datasets. Conclusions: Despite widespread internet access, disparities in telehealth use for ADHD persist. Among 19 SDOH predictors, age (aOR = 0.56), difficulty paying medical bills (aOR = 2.52), and race (aOR = 1.37) were significantly associated with telehealth use, and all ML models outperformed the MVLR benchmark, though bootstrap CIs overlapped. Future research should incorporate inclusive data collection and stratified modeling to better represent disadvantaged populations and inform equitable access strategies. Full article

Most existing driver behavior classification technologies have focused on highways and other primary road infrastructures, despite secondary roads accounting for a disproportionately large number of traffic fatalities worldwide. Compared with highways, secondary roads present greater variability in road geometry, infrastructure quality, and traffic interactions, making driver behavior recognition considerably more challenging. This paper investigates the classification of driver behavior on secondary roads using machine learning techniques. Naturalistic driving data obtained from the publicly available UAH-DriveSet dataset were analyzed using two complementary feature groups describing lane detection and traffic status. Four supervised machine learning algorithms, namely, Logistic Regression (LR), gradient boosting (GB), Random Forest (RF), and Artificial Neural Networks (ANNs), were evaluated to classify driving behavior into three categories: Normal, Aggressive, and Drowsy. The extracted features were first analyzed through statistical profiling and exploratory feature analysis before training and evaluating the classification models. The experimental results show that gradient boosting consistently achieved the highest performance for both feature groups, attaining an overall classification accuracy of approximately 67% while providing balanced precision, recall, and F1-scores across all behavioral classes. Logistic regression and random forest produced competitive but lower performance, whereas the Artificial Neural Network yielded the lowest classification accuracy. The obtained results demonstrate the effectiveness of ensemble learning methods for driver behavior recognition under secondary-road conditions and highlight their potential for integration into intelligent driver monitoring and Advanced Driver Assistance Systems (ADASs). By enabling earlier identification of aggressive and drowsy driving behaviors on secondary roads, the proposed approach could support timely driver warnings and safety interventions, potentially reducing accident risk. Furthermore, the findings provide a benchmark for future machine learning models designed for real-world secondary-road environments, where driving conditions are more variable and challenging than on highways. Full article

Background/Objectives: Healthcare students face an occupational risk of hepatitis B virus (HBV) exposure during clinical training, often many years after receiving their primary vaccination series in infancy or childhood. Progressive waning of anti-hepatitis B surface (anti-HBs) antibody titres, heterogeneous vaccination histories in international student cohorts, high rates of underreported needlestick injuries, and variable occupational health protocols across institutions raise important questions about the adequacy of pre-clinical immunization surveillance in this population. This review aimed to synthesize current evidence on hepatitis B immunization among healthcare students, focusing on occupational exposure risk, seroprotection and immunological memory, clinical management of low or absent anti-HB titres including post-exposure prophylaxis, and the specific challenges posed by multicultural academic settings. Methods: A narrative review was conducted through a systematic literature search of PubMed/MEDLINE and Scopus, covering publications from January 2000 to December 2025, supplemented by key seminal references. After the removal of duplicates and stepwise screening, 49 references were selected for final inclusion. Results: Needlestick and sharps injuries occur at measurable rates during clinical training, with medical students accounting for approximately 30% of occupational exposure events in some series, and with underreporting rates estimated at 19–80% across studies. Pooled seroprotection prevalence at clinical training entry is approximately 73.8% (95% CI 69.1–78.0%), with substantially lower rates among students vaccinated in infancy—as low as 28% at 16–20 years post-vaccination in longitudinal data—compared with adolescence immunization. The majority of students with non-protective titres retain immunological memory, with 90.9% (95% CI 87.7–93.3%) demonstrating an anamnestic response after a single booster dose. Post-exposure prophylaxis pathways depend critically on pre-existing immunological status, reinforcing the operational value of pre-clinical serological screening. International student cohorts present additional complexity due to heterogeneous vaccination schedules, documentation gaps, and variable natural immunity profiles. Conclusions: Systematic pre-clinical serological screening (anti-HBs, HBsAg, and anti-HBc), combined with evidence-based stepwise immunization management and structured educational interventions, is essential to protect healthcare students from occupational HBV exposure. The primary operational goal of screening is the identification of the approximately 5% of true non-responders who require tailored occupational health management. These findings support a proactive, integrated approach to hepatitis B immunization surveillance in healthcare education, aligned with the WHO 2030 viral hepatitis-elimination targets. Full article

Convolutional neural networks (CNNs) are widely used for biomedical image classification, yet it remains unclear under which conditions training on reduced subsets of available data can provide reliable guidance during model development, how much training data is required to achieve stable and comparable performance across CNN architectures, and whether increasing the training set size always leads to improved generalization or can sometimes result in degraded performance. We study this question across four biomedical datasets (breast mammography, pediatric chest X-ray, brain tumor MRI, and skin lesion dermoscopy) using the full grid of 39 CNN architectures (1–3 convolutional layers, 16/32/64 filters) from our companion architectural study, training each configuration from scratch on seven proportions of the training data (5%, 10%, 20%, 40%, 60%, 80%, and 100%) over 5 independent runs per configuration, with the test set held at a fixed size across all sample-size conditions to ensure a like-for-like comparison of generalization performance. The analysis investigates three complementary aspects of sample-size sensitivity: the stabilization of the training–test generalization gap as training-set size increases, the reliability of architecture rankings obtained from reduced training fractions as a proxy for the full-dataset ranking, and the monotonicity of test performance with respect to training-set size. Taken together, the results point to a rough four-band pattern of reliability across the sampled fractions—unstable below $20\%$ of the training set, of uncertain overfitting status between $20\%$ and $60\%$, comparatively stable between $60\%$ and $80\%$, and potentially counterproductive beyond $80\%$—while showing that this pattern is itself dataset-dependent and offers no guarantee on architecture ranking, arguing against reduced-fraction screening as a reliable shortcut for CNN architecture selection in biomedical imaging. All code and datasets are publicly released for reproducibility. Full article

Background: Achieving remission of type 2 diabetes mellitus (T2DM) after bariatric surgery represents a critical opportunity to reduce long-term diabetes-related complications, including cardiovascular disease, nephropathy, neuropathy, and retinopathy. However, remission rates vary widely across patients, and identifying modifiable clinical and behavioral determinants remains essential for optimizing integrated metabolic care. Objectives: In the current study, we aimed to (1) classify type 2 diabetes mellitus (T2DM) remission status after bariatric surgery through clinical, anthropometric, and behavioral variables at follow-up; (2) identify the main model-based determinants of remission status and explainable machine learning using the preoperative model for baseline risk stratification with surgical candidates. Methods: We performed a retrospective cross-sectional study on 233 patients with T2DM who had bariatric surgery at a tertiary referral center. We made use of two analytical frameworks: a full-feature approach to identify the current remission status in a cross-sectional manner and a preoperative approach to make a temporal classification of the baseline for the first time. We trained and internally assessed 14 machine learning and deep learning classifiers. We evaluated model interpretability using SHAP. Results: In the full-feature cross-sectional classification, the Bottleneck Network performed best (ROC AUC = 0.889). SHAP data identified percentage weight regain, pre- and post-surgical body mass index, HbA1c, and oral hypoglycemic agent use as the dominant model-associated factors. In the restricted preoperative setting, the Extra Trees model achieved an AUC of 0.707, which is a lower level but still represents good baseline risk stratification performance. Conclusions: The findings indicate that remission status after bariatric surgery is both clinical as well as behavioral, but the post-operative or contemporaneously assessed variables should be looked at as classification (as opposed to prediction) models. The preoperative model may be able to be used in risk stratification, but clinical validation and prospective evaluation should be made prior to clinical implementation. Full article

Aptamer-based multiplexed proteomic platforms, especially the SOMAmer-based SomaScan assay, are widely used for large-scale discovery of circulating biomarkers relevant to human aging. This review summarizes 42 original research articles published from 2020 through 2026 in which aptamers or aptamer-derived biosensors were used to characterize aging-related biomarkers in human samples or clinically relevant human-disease contexts. The eligible literature falls into several thematic areas: whole-plasma and organ-specific proteomic aging clocks; inflammaging and senescence-associated secretory phenotype (SASP) markers; cardiovascular, metabolic, renal, hepatic, musculoskeletal and neurodegenerative biomarker panels; and aptasensor platforms for detection of individual analytes. Only a small number of studies have compared aptamer- and antibody-based platforms in the same specimens; we tabulate these and show that median between-platform agreement is low to moderate, which constrains the pooling of findings across technologies. We also make explicit an interpretive point that is usually left implicit: because proteomic clocks are trained against chronological age, their correlation with chronological age measures fit to the training target rather than biological validity, and the informative quantity is the residual age gap. In the reviewed literature, SomaScan-based studies are concentrated in cardiovascular, neurodegenerative, frailty, and proteomic aging-clock research, whereas de novo SELEX campaigns targeting aging-specific epitopes and longitudinal human validation of wearable aptasensors were not identified. The main barriers to translation are cross-platform discordance, limited replication across ancestries, under-reported pre-analytical variability, cost, and the research-use-only status of most assays. Full article

Aggregate origin–destination data and summary load factors do not identify train-specific flows; imposing each load factor as an exact margin can therefore overstate precision. We develop an auditable high-speed rail pricing framework combining pooled passenger-kilometer entropy completion, an occupancy-aware pivot logit, link-load equilibrium, and exact-grid Pareto enumeration. Historical train shares guide a sensitivity-tested prior, and target elasticities index fare response. For a reconstructed Beijing–Wuhan case, 97,336 discount vectors are evaluated in each of three core scenarios and candidates are screened across 729 crossed baseline and behavioral scenarios. Under the reference scenario (unit elasticity, crowding-equivalent ratio 0.10, threshold 0.80), the closest-to-ideal admissible vector $(0.94,0.99,0.97)$ increases modeled-service revenue by 0.106% and yields a full-corridor-fare-equivalent surplus gain of 0.803%, with maximum link occupancy of 77.27%. It is admissible in only 368 scenarios and reaches 104.45% occupancy in the most adverse case; only the status quo is admissible in all scenarios. The framework thus identifies scenario-specific opportunities while separating exact numerical evaluation from empirical identification and operational robustness under aggregate-data limitations. Full article

The increasing tourism pressure on the UNESCO World Heritage Altai Mountains calls for efficient environmental monitoring tools. This study presents a Google Earth Engine framework that couples the Remote Sensing Ecological Index (RSEI) with land use/land cover (LULC) mapping to assess ecological changes in the Lake Manzherok area between 2020 and 2025. RSEI was derived from Sentinel-2 and Landsat imagery by combining four indicators (NDVI, MNDWI, NDBSI, LST) through principal component analysis. LULC classification was carried out using Random Forest trained exclusively on Sentinel-2 spectral bands. The results confirm that RSEI effectively captures ecological gradients in complex mountainous terrain, with the first principal component explaining 57–62% of the total variance. While 92% of the study area remained stable, 5.9% showed a decline in ecological status, spatially coinciding with a near doubling of built-up and bare surfaces from 9.89 km² to 18.17 km². The largest negative RSEI changes were associated with transitions from forestland (ΔRSEI = −0.29) and grassland (ΔRSEI = −0.20) to built-up/bare land, whereas reverse transitions displayed positive ΔRSEI values. These spatial patterns are consistent with the visible development related to tourism. However, because the built-up/bare land class also includes naturally bare surfaces, and because interannual climate variability may affect the RSEI components, it is important to interpret the ΔRSEI values as relative changes rather than absolute measurements of tourism impact. The proposed framework provides a reproducible and transferable tool for monitoring ecological quality in data-scarce mountain regions, delivering spatially explicit evidence that can support conservation and land-use planning. Full article

Background: Breast cancer brain metastases (BCBMs) exhibit notable receptor discordance between primary tumors and metastases, yet obtaining intracranial biopsies is rarely practical. We created an interpretable deep learning radiogenomic model to predict estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status from MRI scans in BCBM cases. Methods: A total of 241 post-contrast T1-weighted MRIs from 142 patients were analyzed. We developed a mask-free 3D Residual Neural Network (ResNet) ensemble trained directly on cropped, bias-corrected brain images, with comprehensive 3D geometric and intensity augmentations. The model was optimized in a multi-label setting using Asymmetric Focal Loss. Hyperparameters were fine-tuned via Bayesian optimization, and class probabilities were calibrated. Additionally, Integrated Gradients (IG) offered voxel-level saliency maps. Results: Our ResNet ensemble model achieved a micro-averaged AUROC of 0.74 and a macro-averaged AUROC of 0.67. Receptor-specific AUROCs were 0.57 for ER, 0.79 for PR, and 0.64 for HER2. The F1-scores were 0.56, 0.62, and 0.88 for ER, PR, and HER2, respectively. The held-out cohort contained only four HER2-negative patients, so threshold-dependent HER2 metrics are strongly prevalence-driven and AUROC is the more appropriate summary. Qualitatively inspected saliency maps were concentrated on enhancing metastases with limited background attribution. Conclusions: This proof-of-concept study shows that a segmentation-free, interpretable 3D Convolutional Neural Network (CNN) can be trained to capture receptor-associated patterns in post-contrast T1-weighted MRI of BCBMs. Accuracy was modest relative to published radiomics models, and the mask-free, single-sequence design is offered as a methodological contribution rather than a performance gain. These findings are preliminary, do not establish clinical utility, and require validation in larger, multi-center cohorts. Full article

Background/Objectives: Obesity is a chronic, progressive, and relapsing disease that requires long-term, multidisciplinary management rather than episodic weight-loss treatment. Although novel incretin-based anti-obesity pharmacotherapies, including GLP-1 receptor agonists and dual GIP/GLP-1 receptor agonists, have markedly improved the clinical management of obesity, weight reduction alone does not fully capture treatment success. Body composition, lean mass preservation, physical function, nutritional adequacy, psychological well-being, adherence, and long-term weight-loss maintenance are increasingly recognized as essential therapeutic outcomes. This narrative review critically examines the role of lifestyle medicine as a co-therapeutic strategy during modern anti-obesity pharmacotherapy, with particular attention to physical activity, nutrition, behavioral support, and individualized monitoring. Methods: A narrative literature search was conducted in PubMed up to June 2026. The review included studies addressing adults with overweight or obesity and evidence related to anti-obesity pharmacotherapy, physical activity, nutrition, body composition, functional outcomes, eating behavior, quality of life, treatment tolerability, adherence, weight regain, and long-term maintenance. Results: Current evidence indicates that incretin-based therapies produce substantial and clinically meaningful weight loss, but pharmacological efficacy may be limited by reductions in lean mass, gastrointestinal adverse events, inadequate nutritional intake, treatment discontinuation, and weight regain after drug withdrawal. Physical activity should be considered a therapeutic component rather than only a tool for increasing energy expenditure, as aerobic exercise supports cardiometabolic health and cardiorespiratory fitness, while resistance training helps preserve muscle strength, bone health, and functional capacity. Nutritional strategies are equally important, particularly during appetite suppression, to maintain adequate protein, fiber, fluids, micronutrients, and diet quality. Behavioral factors, including sleep, stress, mood, stigma, self-regulation, and the food environment, may influence adherence and long-term outcomes. Conclusions: Novel anti-obesity drugs should not be viewed as replacements for lifestyle medicine but as powerful tools within an integrated chronic-care model. The goal of treatment should move beyond maximal body-weight reduction to durable improvements in body composition, metabolic health, physical function, nutritional status, quality of life, and weight-loss maintenance. Full article

Background/Objectives: Older adults residing in long-term care facilities (LTCFs) are at increased risk of poor oral health because of functional dependence and limited access to professional oral healthcare. Although oral healthcare education programs for care workers improve knowledge and performance, evidence of their effects on residents’ biological oral health outcomes remains limited. This study evaluated the effects of a care worker-centered oral healthcare program on oral inflammatory status in LTCF residents using salivary interleukin-1 beta (IL-1β) as an objective biomarker. Methods: A single-group pretest–posttest quasi-experimental study was conducted in two LTCFs in the Republic of Korea. Forty care workers completed a structured oral healthcare education program and provided daily oral healthcare to residents for 4 weeks. Saliva samples were collected before and after the intervention, and salivary IL-1β concentrations were measured using enzyme-linked immunosorbent assay. Changes in IL-1β concentrations were analyzed using the Wilcoxon signed-rank, Mann–Whitney U, and Kruskal–Wallis tests. Results: Thirty-seven residents completed the study. Median salivary IL-1β concentrations significantly decreased from 19.33 pg/mL (interquartile range [IQR], 11.49–34.66) at baseline to 10.78 pg/mL (IQR, 0.65–33.64) after the intervention (Z = −3.764, p = 0.001). Greater reductions were observed among residents with greater functional dependence, whereas limited communication ability or oral care refusal was associated with minimal improvement. Conclusions: A care worker-centered oral healthcare program significantly reduced salivary IL-1β concentrations among older adults residing in LTCFs. Findings support care worker training and highlight the use of salivary IL-1β as an objective biomarker for evaluating oral healthcare interventions. Full article

Rising recognition of attention deficit hyperactivity disorder (ADHD) in adults and children is reshaping how Australian health systems organise diagnosis, prescribing and long-term management. This has coincided with sharp increases in ADHD medicine dispensing, high private assessment costs and prolonged waiting times for psychiatrists and paediatricians. Australian states and territories have commenced reforms that expand the role of general practitioners (GPs) in ADHD diagnosis, prescribing and long-term management. This commentary assesses whether these reforms can expand timely and equitable access while maintaining diagnostic accuracy, medication safety and specialist referral. It uses the New South Wales (NSW) model as a detailed exemplar because it has developed a staged pathway: trained continuation prescribers support previously diagnosed patients who are stable on psychostimulant treatment, while endorsed prescribers receive further accredited training or recognition of prior learning to assess, diagnose, initiate and adjust psychostimulant treatment. The commentary distinguishes professional specialty status from ADHD-specific competency: specialist registration in general practice establishes the professional status of qualified Australian GPs, whereas safe extension of ADHD diagnosis and psychostimulant prescribing requires condition-specific education, competency assessment, prescribing authority, monitoring and defined referral pathways. It reviews Australian reforms, explains the NSW training and governance pathway, compares overseas approaches, and identifies safeguards needed to avoid diagnostic compression, overdiagnosis, stimulant diversion and widening inequity. The central argument is that GP involvement should be framed as trained, governed primary-care capacity. If adequately funded, audited and linked to specialist escalation pathways, the model may reduce access barriers while preserving diagnostic rigour. Full article

Objective: To examine acute BEFORE–AFTER changes in maximum, mean, and median surface-EMG RMS amplitudes recorded from four shoulder-girdle muscles around scheduled collegiate volleyball training sessions. Methods: Sixteen male collegiate volleyball players representing one university team participated in this exploratory prospective repeated-measures study. Surface EMG was recorded from the upper trapezius, lower trapezius, infraspinatus, and serratus anterior during muscle-specific maximal voluntary isometric effort tasks. A standardized dynamic warm-up was completed before the BEFORE assessment. Surface EMG was then recorded immediately after warm-up and before the volleyball-specific training components of the session (BEFORE), and again within 5–10 min after completion of the scheduled team-training session (AFTER), on three weekly measurement days. For each EMG outcome, the main inferential estimand was the marginal AFTER–BEFORE contrast averaged across muscles and measurement days. Linear mixed-effects models included assessment condition, muscle, measurement day, and the assessment condition × muscle term; interaction analyses were treated as exploratory because the participant-level sample comprised 16 independent experimental units. Marginal AFTER–BEFORE contrasts were adjusted across the three RMS-amplitude outcomes using the Bonferroni method. Results: Mean RMS amplitude was lower AFTER than BEFORE the training sessions by 4.16 µV (95% CI: −6.32 to −2.01; Bonferroni-adjusted p < 0.001). Maximum RMS amplitude was also lower by 5.77 µV (95% CI: −11.19 to −0.35), but this contrast was not supported after multiplicity adjustment (adjusted p = 0.115). Median RMS amplitude showed an estimated increase of 3.88 µV (95% CI: −0.19 to 7.94; adjusted p = 0.181). Exploratory assessment condition × muscle interactions were not statistically significant for any of the three RMS-amplitude outcomes. Conclusions: Only the decrease in mean RMS amplitude remained statistically supported after adjustment across the three EMG outcomes. Because both assessments were performed after the standardized warm-up, warm-up status was held constant with respect to completion of the warm-up. The AFTER assessment additionally followed the subsequent volleyball-specific training components and a 5–10-min post-session interval. Accordingly, the contrast represents a within-session AFTER–BEFORE difference associated with the intervening training exposure and temporal/order effects rather than an isolated causal effect of training. Exploratory condition × muscle interactions were not statistically significant, but the small sample does not establish equivalent responses among muscles. The findings do not establish altered mechanical force or localized neuromuscular fatigue. Full article