Search Results (5,204)

Objective: This study aims to investigate the protective effect of Shengmai San (SMS) against high-glucose (HG)-induced injury in neonatal rat ventricular myocytes (NRVMs) and to elucidate the underlying pharmacological molecular mechanisms. We hypothesize that SMS ameliorates HG-induced calcium homeostasis imbalance in NRVMs by improving mitochondrial energy metabolism disorder, and this protective effect is associated with the downregulation of oxidized and phosphorylated CaMKII expression to inhibit CaMKII signaling pathway overactivation. Herein, we verify this hypothesis by assessing mitochondrial function, calcium transients, sarcoplasmic reticulum (SR) calcium handling and CaMKII phosphorylation levels in NRVMs. Methods: First, ultra-high performance liquid chromatography–high resolution mass spectrometry was used to identify the chemical components of SMS to clarify its material basis. Primary NRVMs were then cultured under low-glucose (LG) or HG conditions, with 2% SMS-medicated serum (SMS-MS) as the experimental intervention, and NAC (ROS scavenger) and KN93 (CaMKII inhibitor) as positive controls. Following intervention, we sequentially detected key indicators corresponding to the proposed pathological pathway: intracellular reactive oxygen species (ROS) levels (oxidative stress), mitochondrial ROS, mitochondrial function indices including oxygen consumption rate (OCR) (energy metabolism), calcium transients and diastolic intracellular free calcium concentration (global calcium homeostasis), sarcoplasmic reticulum (SR) calcium leak (calcium handling disorder), and, finally, the phosphorylation, oxidation levels of CaMKII and RyR2 phosphorylation (Ser2814) (p-RyR2) (key regulatory pathway) via Western blot to systematically elucidate the mechanistic link between SMS intervention and HG-induced NRVM injury. Results: Quantitative analysis revealed that high-glucose (HG) induction significantly reduced calcium transient amplitude and prolonged the decay time constant (tau) in NRVMs at 72 h (p < 0.01 vs. LG), with these parameters normalizing by 120 h—an effect indicative of a compensatory adaptive response. The 2%SMS-MS markedly ameliorated HG-induced calcium transient abnormalities at 72 h (p < 0.01 vs. HG). Additionally, 2%SMS-MS significantly enhanced mitochondrial basal oxygen consumption rate, spare respiratory capacity, ATP production, and maximal respiration in HG-exposed NRVMs (p < 0.01 vs. HG). SMS also significantly reduced intracellular reactive oxygen species (ROS) levels (p < 0.01 vs. HG), mitochondrial ROS levels (p < 0.01 vs. HG), diastolic intracellular free calcium concentration (p < 0.01 vs. HG), and SR calcium leak (p < 0.05 vs. HG). Western blot analysis revealed that 2%SMS-MS intervention effectively downregulated the expression of oxidized CaMKII (Ox-CaMKII) (p < 0.01 vs. HG), phosphorylated CaMKII (p-CaMKII) (p < 0.01 vs. HG), and RyR2 phosphorylation (Ser2814) (p < 0.05 vs. HG), which may be the potential mechanism in maintaining calcium homeostasis in HG-induced NRVMs. Conclusions: This study suggests that SMS enhances mitochondrial energy metabolism and exerts a protective effect against high-glucose-induced calcium homeostasis imbalance in NRVMs, which supports our proposed hypothesis. Its potential mechanism indicates that the protective effects of SMS are associated with its ability to downregulate the expression of oxidized and phosphorylated CaMKII. These findings highlight SMS as a potential therapeutic candidate for alleviating HG-related myocardial injury and provide evidence for its application in the prevention of early diabetic cardiomyopathy. Full article

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines. Full article

Background and Objectives: Visual evoked potentials (VEPs) are a simple, noninvasive method for detecting subclinical visual pathway involvement in multiple sclerosis. This study investigated the frequency of VEP abnormalities and their associations with baseline clinical, radiological, and cerebrospinal fluid (CSF) features in treatment-naïve patients with clinically isolated syndrome (CIS) or early relapsing-remitting multiple sclerosis (RRMS) without prior optic neuritis. Materials and Methods: We retrospectively reviewed newly diagnosed, treatment-naïve CIS/early RRMS patients evaluated between January 2022 and July 2024 who underwent CSF analysis. Pattern-reversal VEPs were recorded under standardized conditions. VEP abnormalities were analyzed as any or bilateral, and associations were assessed using group comparisons and multivariable logistic regression. Results: In 101 patients (mean age 31.8 ± 9.7 years; 72% female; median EDSS 1.0), latency prolongation occurred in 69 (42 any,27 bilateral) and amplitude reduction in 33 (22 any, 11 bilateral). Among patients with latency prolongation, both the number of OCB bands and the IgG index were higher (bilateral p = 0.032; any p = 0.007). In multivariable analysis, male sex (p = 0.032) and pyramidal/brainstem-onset presentation (p = 0.006) were independently associated with any amplitude reduction; neither was associated with latency abnormalities. Conclusions: VEP abnormalities are common early in the disease, even without a history of optic neuritis. Male sex and pyramidal/brainstem-onset presentation were associated with reduced amplitude, suggesting that amplitude decrease may reflect early tissue dysfunction and may be related to adverse baseline clinical features. Associations between intrathecal immune activation and prolonged latency may indicate subclinical demyelination of the visual pathways related to inflammatory activity. Larger longitudinal studies are needed to clarify the clinical significance of VEP abnormalities in early RRMS. Full article

Unsupervised video anomaly detection (VAD) methods learn from normal data to identify anomalies by capturing pattern deviations. However, they often struggle to model multi-scale features and distinguish between normal and abnormal instances. To address these limitations, we propose a Multi-scale U-shaped Adaptive Clustering Learning (MS-UACL) framework. Built on the U-Net architecture, we redesign it as a 3D-encoder/2D-decoder autoencoder. In the encoder, we introduce a Dual-scale Feature Cascading Module (IDCN), which adopts a pseudo-branch fusion mechanism to systematically model multi-scale spatiotemporal features, thereby enhancing the model’s representational capability. To further enhance the distinction between normal and anomalous patterns, we propose an MLP-based Adaptive Clustering Algorithm (MLP-ACA). Specifically, MLP-ACA employs an initial mapping mechanism to align cluster centers with the underlying normal data distribution, facilitating more accurate feature reconstruction. Additionally, we introduce an adaptive clustering update strategy that optimizes cluster centers by tuning solely the parameters of the MLP. This enables the cluster centers to autonomously converge toward optimal feature representations, thereby accelerating clustering convergence and enhancing pattern separability. Extensive experiments on three benchmark datasets demonstrate that the proposed MS-UACL framework outperforms most existing methods on small- and medium-scale datasets. Full article

Background: Low-dose computed tomography (LDCT) lung cancer screening (LCS) frequently identifies emphysema in high-risk smokers. However, the extent to which CT-detected emphysema reflects underlying physiological impairment remains uncertain. We evaluated whether spirometry can detect functional abnormalities in this population beyond structural imaging findings. Methods: This cross-sectional study included 323 individuals with LDCT- detected emphysema and no lung cancer or prior chronic respiratory diseases within a screening cohort (n = 3076). Participants underwent pre-bronchodilator spirometry and symptom assessments (COPD Assessment test (CAT) and Modified Medical Research Council (mMRC) Dyspnea Scale). Pre-bronchodilator airflow limitation was defined as forced expiratory volume in one second to forced vital capacity ratio (FEV₁/FVC) < 0.70. Small airways dysfunction was defined by ≥2 reduced mid-expiratory flow parameters (<60% predicted). Flow–volume curve morphology was assessed qualitatively. Results: Pre-bronchodilator airflow limitation was observed in 45.2% of participants, predominantly mild. Small-airway dysfunction was present in 52%, and an abnormal flow–volume curve morphology in 67.5%. Notably, functional abnormalities were frequently observed despite preserved FEV₁. Symptom burden was low, with only 7.7% of participants reporting clinically significant symptoms. Functional impairments often overlapped and were common in minimally symptomatic individuals. Conclusions: In a lung cancer screening (LCS) cohort with CT-detected emphysema, functional abnormalities are frequently observed, including in individuals with preserved FEV₁ and minimal symptoms. Spirometry provides additional physiological insight beyond structural imaging; however, these findings are descriptive and should not be interpreted as diagnostic of COPD. Further studies are needed to determine their clinical relevance. Full article

Background: The evaluation of renal function in neonates is challenging due to maternal creatinine transfer, reduced muscle mass, and non-steady-state physiology. Cystatin C emerged as a promising biomarker for assessing neonatal glomerular filtration rate. This review summarizes evidence from studies evaluating serum and urine cystatin C in healthy neonates and high-risk groups, including preterm newborns, neonates with acute kidney injury, and those with congenital kidney and urinary tract defects. Methods: Twenty studies were included and qualitatively synthesized following PRISMA guidelines. Results: In the included studies, serum cystatin C exhibited consistent postnatal patterns independent of maternal influence and showed a strong correlation with gestational age and renal development. Cystatin C enabled earlier detection of renal dysfunction compared to serum creatinine, especially in preterm infants and critically ill neonates. In babies with congenital renal abnormalities, cystatin C levels were associated with disease severity and clinical outcomes, while the cystatin C-based estimated glomerular filtration rate surpassed creatinine-based estimations. Urinary cystatin C correlated with tubular damage and increased risk of chronic kidney disease during follow-up. Conclusions: Cystatin C is a reliable biomarker for evaluating neonatal renal function, although further standardization and validation are required for clinical implementation. Full article

This study develops a data-driven framework for predictive maintenance and prognostic health management in industrial systems using edge-enabled predictive algorithms. The objective is to support early identification of abnormal operating conditions and improve maintenance decision making under real production environments. The proposed approach combines edge-level monitoring, anomaly detection, and predictive modeling to analyze operational signals and estimate system health conditions from high-frequency industrial data. Empirical validation was conducted using operational datasets collected from two industrial production facilities between 2024 and 2025. The model evaluates patterns associated with operational instability and degradation-related anomalies and translates them into interpretable health indicators that can support proactive intervention. The empirical results show strong predictive performance, with R² reaching 0.989, a mean absolute percentage error of 3.67%, and a root mean square error of 0.79. In addition, the mitigation of early anomaly signals was associated with an observed improvement of approximately 3.99% in system stability. Unlike many existing studies that treat anomaly detection, predictive modeling, and prognostic analysis as separate tasks, the proposed framework connects these stages within a unified analytical structure designed for deployment in industrial environments. The findings indicate that edge-generated anomaly signals can provide meaningful early information about potential system deterioration and can assist in planning timely maintenance actions even when explicit failure labels are limited. The study contributes to the development of scalable predictive maintenance solutions that integrate artificial intelligence with edge-based industrial monitoring systems. Full article

Cardiovascular and metabolic diseases (CMDs) are the leading causes of global mortality. While university students represent a critical demographic for early intervention, conventional univariate screenings often fail to capture the synergistic interactions between lipid abnormalities and adiposity. This study aimed to identify and characterize multidimensional cardiometabolic phenotypes in Ecuadorian university students using multivariate exploratory techniques. A cross-sectional study was conducted with 365 students from the Coastal (n = 193) and Andean (n = 172) regions of Ecuador. Lipid profiles (TC, HDL-c, LDL-c, triglycerides), body composition (body fat percentage, visceral fat via bioelectrical impedance), and blood pressure were analyzed. Data were processed using HJ-Biplot analysis for dimensional reduction and a hybrid clustering approach (Hierarchical and K-means) for population segmentation. The HJ-Biplot explained 72.3% of the total variance. The first principal component (PC1, 49.2%) was associated with morphometric size (weight, height), while the second (PC2, 23.1%) was dominated by adiposity markers (body fat and visceral fat). Three distinct clusters were identified: Cluster 0 (27.1%, predominantly female) represented a low-risk profile with the highest HDL-c (57.5 mg/dL); Cluster 1 (26.6%, majority male) exhibited an intermediate-risk profile with the highest triglycerides (117.9 mg/dL); and Cluster 2 (46.3%, almost exclusively male and Andean-dominant) presented the highest risk, characterized by the lowest HDL-c levels (41 mg/dL) and older age. In conclusion, cardiometabolic risk is heterogeneously distributed across sex and geographical regions. Multivariate profiling allows for the detection of early metabolic vulnerability that remains undetected in traditional screenings. These findings support the implementation of targeted public health strategies tailored to the specific phenotypic and regional characteristics of the university population in Ecuador. Full article

Accurate estimation of battery state of health (SoH) is an important aspect for improving the reliability, safety, and operating efficiency of an energy storage system. This study presents a unified deep learning pipeline for prediction, latent feature extraction, and anomaly detection. A convolution neutral network autoencoder is used to learn compact latent features from a dataset (NASA battery datasets, i.e., B0005, B0006, B0007, and B0018). These features serve as inputs to random forest and linear regression models, which are further compared with the CNN and GRU. The system is evaluated using leave-one-group-out cross-validation to ensure robustness across different batteries. Latent space quality is studied using PSA, t-SNE, and UMAP analyses. Furthermore, clustering performance is measured using the Silhouette Score, and anomalies are detected using reconstruction error and the Isolation Forest technique. The obtained results show that the AE+RF model achieves the best performance, with a 0.0285 root mean square value (RMSE) and a 0.0109 mean absolute error (MAE), with a high 0.96 coefficient of determination (R²). It is evident that AE+RF shows high prediction accuracy and model reliability. The results show that latent features improve prediction accuracy, helping to clearly separate normal and abnormal patterns, providing a robust and accurate approach to battery SoH estimation that is suitable for battery management system applications. Full article

Aims. To investigate the relationship between ultrasound (US)-detected parenchymal abnormalities in the major salivary glands (MSG), joint and tendon inflammation, and systemic disease activity in patients with primary Sjögren’s syndrome (pSS). Patients and methods. This cross-sectional, multicenter study enrolled 60 patients with pSS and 20 healthy controls (HCs). Systemic disease activity was evaluated using the EULAR Sjögren’s Syndrome Disease Activity Index (ESSDAI), while symptom burden was assessed with the EULAR Sjögren’s Syndrome Patient Reported Index (ESSPRI). MSG evaluation included bilateral gray-scale (GS) and power Doppler (PDUS) assessment of the parotid and submandibular glands using a semi-quantitative 0–3 scoring system. Musculoskeletal ultrasound (MSUS) assessment comprised bilateral examination of the wrists, second to fifth metacarpophalangeal (MCP) and proximal interphalangeal (PIP) joints, the fourth extensor wrist compartment, and the flexor tendons of the second to fifth fingers for GS and PD-detected synovitis and tenosynovitis, also scored semi-quantitatively. Recorded outcomes included GS and PD synovitis scores, total synovitis score, tenosynovitis score, GS and PD glandular scores, and total glandular score. Results. Synovitis was most frequently detected in the wrists, followed by the second PIP joint. Subclinical synovitis—defined as a GSUS synovitis score > 0 in a joint without clinical swelling—was detected in 66.7% (n = 28) of patients with pSS. No significant correlations were found between joint US scores and salivary gland US scores. ESSPRI showed moderate positive correlations with both the GS synovitis score (p = 0.002) and the total synovitis score (p = 0.003), as well as significant positive correlations with all salivary gland US scores: GS (p < 0.001), PD (p = 0.002), and total glandular score (p < 0.001). ESSDAI demonstrated only a weak positive correlation with the GS salivary gland score (p = 0.030). Conclusions. In patients with pSS, the extent of US-detected MSG parenchymal abnormalities does not reflect systemic disease activity and does not correlate with US-detected joint synovitis. In contrast, patient-reported symptom burden is associated with both joint inflammation and MSG parenchymal changes on US. Larger studies are needed to further define the role of salivary gland and joint US in evaluating disease activity in pSS. Full article

Background: Gaucher disease (GD) is a rare lysosomal storage disorder caused by mutations in the GBA1 gene. Traditionally, GD is classified into three subtypes based on the severity of neurological involvement; however, overlapping clinical features increasingly suggest a continuum of phenotypes rather than distinct categories. In this prospective observational cohort study, we conducted a multidisciplinary assessment of patients with GD to identify and monitor neurological, cognitive, auditory, and visual impairments. Materials and Methods: A comprehensive clinical and instrumental evaluation was performed at baseline and repeated at follow-up, with a median interval of 37 months (IQR 36–38). Neurological assessments included physical examination, clinical rating scales, video-EEG, and brain MRI. Cognitive status was assessed using a standardized battery of neuropsychological tests. Detailed audiological and ophthalmological evaluations were also conducted. Paired parametric or non-parametric tests were applied as appropriate, with Bonferroni correction for cognitive outcomes (p < 0.05). Results: Of the 22 patients assessed at baseline, 18 completed the follow-up evaluation. Neurological assessments showed a worsening of subtle parkinsonian signs, with significant increases in Movement Disorder Society–Unified Parkinson’s Disease Rating Scale Part III scores (p = 0.04) and non-motor symptom scores (p = 0.01). Two of the eighteen patients developed epilepsy during follow-up. A high prevalence of sleep disturbances was confirmed, with 27.8% exhibiting excessive daytime sleepiness and 16.7% reporting REM sleep behaviour disorder on standardized questionnaires. Compared with baseline, cognitive assessments revealed a higher proportion of patients with performance below normative population scores in at least one cognitive domain, particularly memory. Sensorineural hearing loss was confirmed in 11 of 15 patients (73.3%) who underwent audiological evaluation, with progressive worsening of audiometric thresholds observed in 7 of 11 (64%). Ophthalmological evaluations showed no changes in visual acuity or OCT findings; however, multifocal electroretinography abnormalities were detected in 12 of 13 patients. Conclusions: Through in-depth phenotyping, this study identifies measurable neurological, cognitive, and sensory progressive changes in patients with GD over time, supporting the value of tailored, multidisciplinary long-term care strategies to monitor and address emerging clinical needs in this rare disease. Full article

Background and Clinical Significance: Uterine smooth muscle tumors range from benign leiomyomas to highly aggressive leiomyosarcomas. Smooth muscle tumors of uncertain malignant potential (STUMP) represent an intermediate and diagnostically challenging category defined by borderline or discordant histological features. Their clinical management remains complex due to limited possibilities for reliable preoperative differentiation and the absence of clearly established surveillance protocols. The situation becomes particularly sensitive in postmenopausal patients, in whom tumor growth or abnormal bleeding raises concern for malignancy. Case Presentation: We report a 66-year-old postmenopausal woman presenting with persistent uterine bleeding and interval growth of a previously presumed leiomyoma. Transvaginal ultrasound demonstrated a heterogeneous intramural mass measuring approximately 5–7 cm, while endometrial sampling revealed inactive, atrophic endometrium without evidence of malignancy. Given the patient’s postmenopausal status and progressive symptoms, total abdominal hysterectomy with bilateral adnexectomy was performed. Histopathological examination identified moderate cytological atypia, focal coagulative tumor necrosis, and mitotic activity of up to five mitoses per ten high-power fields, findings insufficient for leiomyosarcoma but exceeding those expected for a benign leiomyoma. A diagnosis of STUMP was established. Postoperative staging showed no residual or metastatic disease, and structured long-term follow-up was initiated. Discussion: This case illustrates the limitations of current preoperative diagnostic tools in distinguishing between benign and borderline or malignant uterine smooth muscle tumors. Clinical presentation, imaging, and endometrial sampling were not predictive of the final diagnosis. In postmenopausal women, enlargement of a presumed leiomyoma should prompt careful evaluation, as histological assessment after complete surgical removal often remains the only reliable method of diagnosis. The unpredictable biological behavior of STUMP and reported cases of late recurrence support the need for prolonged surveillance, even after apparently adequate surgical treatment. Conclusions: STUMP remains primarily a postoperative diagnosis and represents a persistent gray zone in gynecologic oncology. Postmenopausal tumor growth and abnormal bleeding warrant an individualized and cautious approach. Careful histopathological evaluation and long-term follow-up are essential to ensure early detection of possible recurrence and optimal patient management. Full article

This study presents a scalable decision support system (DSS) framework designed to meet the growing demands of instant data-driven decision-making environments. The architecture integrates key technologies, including Apache Kafka for parallel data streaming, a Python-based data analytics module for distributed processing, JWT-based secure user authentication, and WebSocket communication for instantaneous prediction delivery. The system performs mitochondrial localization in electron microscopy (EM) images using multiple versions of the YOLO (You Only Look Once) object detection model. The publicly available CA1 Hippocampus dataset was used for detection evaluation. Among the evaluated models, YOLOv10x achieved the highest detection performance, yielding a mean average precision (mAP) score of 95.2%. Experimental evaluations of the DSS were conducted under simulated load conditions using the Artillery tool to assess the system’s scalability and responsiveness. Empirical results indicate consistent low-latency performance across varying consumer group sizes, confirming the architecture’s ability to scale the analytics module horizontally without compromising responsiveness. These findings validate the system’s suitability for just-in-time decision support applications. In particular, the system may support clinicians in the task of mitochondrial analysis, where structural abnormalities can be indicative of pathological conditions, including cancer. By enabling early detection of such abnormalities, the proposed framework has the potential to contribute to the timely diagnosis of diseases such as cancer. The proposed study differs from existing studies by combining deep learning with real-time scalable data processing technologies, such as Kafka and WebSocket, in a web-based DSS application for mitochondria detection. Full article

Preterm birth interrupts critical phases of lung development and is associated with long-term alterations in respiratory structure and function. While bronchopulmonary dysplasia (BPD) has traditionally been considered the principal determinant of adverse outcomes, accumulating evidence indicates that prematurity per se contributes substantially to persistent pulmonary impairment. Lung function trajectories in preterm-born children frequently track along lower percentiles from infancy into adolescence and early adulthood, with limited catch-up growth and increased vulnerability to chronic airflow limitation. Assessment of lung function requires a developmentally tailored approach, as feasibility and interpretability vary across age groups. In infancy, non-volitional techniques such as tidal breathing flow-volume loop analysis and raised-volume rapid thoracoabdominal compression allow early evaluation of respiratory mechanics. During toddlerhood, methodological limitations persist, although emerging technologies may expand feasibility. In preschool children, impulse oscillometry enables detection of small airway dysfunction, often preceding spirometric abnormalities. From school age onward, spirometry, body plethysmography, diffusing capacity, and multiple breath washout provide complementary information on obstructive, restrictive, and gas-exchange impairments. Longitudinal studies demonstrate that reduced lung function is not confined to children with BPD and may predispose to early-onset chronic obstructive pulmonary disease-like phenotypes. Early identification of abnormal trajectories and modifiable risk factors supports structured long-term follow-up and preventive strategies. Standardization of age-specific assessment protocols and harmonization of reference values are essential to improve risk stratification and optimize long-term respiratory outcomes in this vulnerable population. Full article

Generator faults are among the most expensive events in utility-scale wind turbines, and the remaining useful life (RUL) of a generator is strongly influenced by long-term thermal loading on windings and bearings. Although wind farms continuously log multi-point generator temperatures and operating variables via SCADA, these data are rarely converted into an actionable, quantitative RUL trajectory that can be used directly for maintenance planning. This study proposes a field-oriented RUL estimation framework that transforms multi-year SCADA records into degradation-focused indicators and converts them into a physically plausible, decision-ready RUL curve. First, SCADA data are cleaned and filtered by operating conditions, and temperature rises relative to ambient are extracted. Next, abnormal operation is detected and summarised using an abnormal operation index (AOI), and thermal severity indicators are aggregated into a health index (HI) that reflects both proximity to engineering limits and signal variability. The HI is then mapped to lifetime consumption to update an effective age relative to the generator’s designed lifetime, followed by smoothing and monotonicity enforcement to ensure a stable, non-increasing RUL trajectory. Field validation shows a highly smooth RUL profile (98.2%) and a near-linear long-term decreasing trend ($R^2=0.985$). The results demonstrate that SCADA temperature–operation data can support reliable online generator RUL prognostic monitoring without the need for additional sensors. Full article