Search Results (2,349)

Cardiovascular diseases (CVDs) remain the leading cause of global mortality, with ischemic heart disease (IHD) being the most prevalent and deadly subtype. The growing burden of IHD underscores the urgent need for effective early detection methods that are scalable and non-invasive. Heart Rate Variability (HRV), a non-invasive physiological marker influenced by the autonomic nervous system (ANS), has shown clinical relevance in predicting adverse cardiac events. This study presents a photoplethysmography (PPG)-based Zhurek IoT device, a custom-developed Internet of Things (IoT) device for non-invasive HRV monitoring. The platform’s effectiveness was evaluated using HRV metrics from electrocardiography (ECG) and PPG signals, with machine learning (ML) models applied to the task of early IHD risk detection. ML classifiers were trained on HRV features, and the Random Forest (RF) model achieved the highest classification accuracy of 90.82%, precision of 92.11%, and recall of 91.00% when tested on real data. The model demonstrated excellent discriminative ability with an area under the ROC curve (AUC) of 0.98, reaching a sensitivity of 88% and specificity of 100% at its optimal threshold. The preliminary results suggest that data collected with the “Zhurek” IoT devices are promising for the further development of ML models for IHD risk detection. This study aimed to address the limitations of previous work, such as small datasets and a lack of validation, by utilizing real and synthetically augmented data (conditional tabular GAN (CTGAN)), as well as multi-sensor input (ECG and PPG). The findings of this pilot study can serve as a starting point for developing scalable, remote, and cost-effective screening systems. The further integration of wearable devices and intelligent algorithms is a promising direction for improving routine monitoring and advancing preventative cardiology. Full article

Background: Early detection of dysglycemia in young adults is important but underexplored. This study aimed to (1) predict long-term changes in fasting plasma glucose (δ-FPG) and (2) classify future prediabetes using complementary machine learning (ML) approaches. Methods: We analyzed 6247 Taiwanese men aged 18–35 years (mean follow-up 5.9 years). For δ-FPG (continuous outcome), random forest, stochastic gradient boosting (SGB), eXtreme gradient boosting (XGBoost), and elastic net were compared with multiple linear regression using Symmetric mean absolute percentage error (SMAPE), Root mean squared error (RMSE), Relative absolute error(RAE), and Root relative squared error (RRSE) Sensitivity analyses excluded baseline FPG (FPG_base). Shapley additive explanations(SHAP) values provided interpretability, and stability was assessed across 10 repeated train–test cycles with confidence intervals. For prediabetes (binary outcome), an XGBoost classifier was trained on top predictors, with class imbalance corrected by SMOTE-Tomek. Calibration and decision-curve analysis (DCA) were also performed. Results: ML models consistently outperformed regression on all error metrics. FPG_base was the dominant predictor in full models (100% importance). Without FPG_base, key predictors included body fat, white blood cell count, age, thyroid-stimulating hormone, triglycerides, and low-density lipoprotein cholesterol. The prediabetes classifier achieved accuracy 0.788, precision 0.791, sensitivity 0.995, ROC-AUC 0.667, and PR-AUC 0.873. At a high-sensitivity threshold (0.2892), sensitivity reached 99.53% (specificity 47.46%); at a balanced threshold (0.5683), sensitivity was 88.69% and specificity was 90.61%. Calibration was acceptable (Brier 0.1754), and DCA indicated clinical utility. Conclusions: FPG_base is the strongest predictor of glycemic change, but adiposity, inflammation, thyroid status, and lipids remain informative. A dual interpretable ML framework offers clinically actionable tools for screening and risk stratification in young men. Full article

Background/Objectives: Pain neuroscience education (PNE) has demonstrated efficacy in adults with chronic pain, but the pediatric evidence is still developing, despite its increasingly frequent use. Evidence for the effectiveness of PNE in pediatrics remains fragmented across settings and outcomes, which justifies a systematic evaluation focused on children and adolescents. Methods: Following PRISMA, two reviewers independently screened records (PubMed, Web of Science, PEDro; through 21 July 2025), extracted data, and assessed risk of bias (RoB 2 for randomized controlled trials; NIH/CASP for non-randomized studies). Given the heterogeneity, we conducted a structured narrative synthesis (SWiM) and rated the certainty of evidence with GRADE. PROSPERO: CRD420251062922. Results: Eleven studies met the inclusion criteria. PNE consistently improved pain-related knowledge, with effects maintained at follow-up (moderate certainty); effects on pain intensity, function, and emotional outcomes were small and inconsistent (low certainty), with more favorable patterns when PNE was combined with exercise and/or booster sessions. Digital and gamified formats proved feasible and engaging; parental outcomes showed small improvements where measured. Conclusions: PNE is a promising, low-cost, and scalable component of pediatric chronic pain care, strengthening self-efficacy and adaptive coping. Integration into biopsychosocial, multidisciplinary programs—particularly alongside exercise and family involvement—may optimize outcomes. Larger, standardized trials with long-term follow-up and systematic adverse-event reporting are needed to solidify guidance for clinical practice. Full article

The morbidity/mortality risks of cystic fibrosis (CF) with a delayed diagnosis have made newborn screening (NBS) attractive for the past 50 years. Initial efforts focused on meconium analyses, but these proved unsatisfactory. After dried blood spot specimens became valuable for NBS applied to other genetic disorders and immunoassay methods became routine, the discovery of immunoreactive trypsinogen (IRT) led to numerous CF NBS programs around the world. Excellent laboratorians led the way, but CF clinicians rightly questioned the benefit–risk relationship and unanswered questions about IRT. These issues were resolved by the combination of a positive randomized clinical trial and the discovery of the cystic fibrosis transmembrane conductance regulator gene (CFTR) and its principal pathogenic variant, F508del. Recommendations for universal screening and then the proliferation of IRT/DNA screening programs followed. But more knowledge has brought more complexity, including an enigmatic, distracting condition known as cystic fibrosis transmembrane conductance regulator-related metabolic syndrome (CRMS) or cystic fibrosis screen positive, inconclusive diagnosis (CFSPID). Recently, with the recognition that CF is not a “white person’s disease,” and that over 1000 CFTR pathogenic variants occur, attention has turned to achieving equity and timeliness for all babies. Continuous quality improvement has characterized the past decade, as greatly expanded CFTR panels in the DNA tier through next-generation sequencing offer promise and raise the prospect of a primary genetic screening test. Full article

The continuous growth in global demand for mineral resources and the increasing difficulty of mineral exploration have created bottlenecks for traditional mineral prediction methods in handling complex geological information and large amounts of data. This review aims to explore the latest research progress in machine learning technology in the field of large-scale mineral prediction from 2016 to 2025. By systematically searching the Web of Science core database, we have screened and analyzed 255 high-quality scientific studies. These studies cover key areas such as mineral information extraction, target area selection, mineral regularity modeling, and resource potential evaluation. The applied machine learning technologies include Random Forests, Support Vector Machines, Convolutional Neural Networks, Recurrent Neural Networks, etc., and have been widely used in the exploration and prediction of various mineral deposits such as porphyry copper, sandstone uranium, and tin. The findings indicate a substantial shift within the discipline towards the utilization of deep learning methodologies and the integration of multi-source geological data. There is a notable rise in the deployment of cutting-edge techniques, including automatic feature extraction, transfer learning, and few-shot learning. This review endeavors to synthesize the prevailing state and prospective developmental trajectory of machine learning within the domain of large-scale mineral prediction. It seeks to delineate the field’s progression, spotlight pivotal research dilemmas, and pinpoint innovative breakthroughs. Full article

Introduction: Evidence on orthodontic interventions for temporomandibular disorders (TMD) is fragmented and inconclusive, creating a gap in guidance for clinical decision-making. This study addresses that gap by evaluating current knowledge on these interventions. Methods: A PRISMA-ScR scoping review was conducted with a systematic search of PubMed, Scopus, and Web of Science (2018–2023). Eligible studies were peer-reviewed, English-language, human studies examining TMD treatment and/or etiology. Three independent reviewers screened records and extracted data and a fourth reviewer performed random audits. Results: Of 899 records, 10 studies met inclusion criteria (non-surgical, n = 7: 4 case reports, 2 prospective, 1 longitudinal; combined orthodontic–surgical, n = 3: 1 case report, 2 longitudinal; participant ages 15–71 years). Diagnostics included imaging, clinical examination, occlusal analysis, and questionnaires, although few used RDC/TMD or DC/TMD criteria. Non-surgical orthodontic modalities (fixed appliances, camouflage, TADs, stabilization splints) showed mixed results, with several studies reporting short-term symptom improvement, while others found no effect on TMD onset or progression. Combined orthodontic–surgical approaches (e.g., bilateral sagittal split osteotomy, Le Fort I) also showed variable outcomes. Conclusions: Low-to-moderate quality evidence suggests that orthodontic-surgical interventions may alleviate TMD symptoms in select patients; however, heterogeneity and limited use of standardized diagnostics constrain the certainty of these findings. Future research should prioritize DC/TMD-based diagnostics, core outcomes, comparative designs, and ≥12–24 months of follow-up to identify prognostic factors and responsive subgroups. Full article

Inadequate screening of features and insufficient extraction of multi-source time-series data potentially result in insensitivity to historical noise and poor extraction of features for PM_2.5 concentration prediction models. Precipitable water vapor (PWV) data obtained from the Global Navigation Satellite System (GNSS), along with air quality and meteorological data collected in Suzhou city from February 2021 to July 2023, were employed in this study. The Spearman correlation analysis and Random Forest (RF) feature importance assessment were used to select key input features, including PWV, PM₁₀, O₃, atmospheric pressure, temperature, and wind speed. Based on RF, Long Short-Term Memory (LSTM), and Multilayer Perceptron (MLP) algorithms, four PM_2.5 concentration prediction models were developed using sliding window and fusion algorithms. Experimental results show that the root mean square error (RMSE) of the 1 h PM_2.5 concentration prediction model using the RF-LSTM fusion algorithm is 4.36 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, while its mean absolute error (MAE) and mean absolute percentage error (MAPE) values are 2.63 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$ and 9.3%. Compared to the individual LSTM and MLP algorithms, the RMSE of the RF-LSTM PM_2.5 prediction model improves by 34.7% and 23.2%, respectively. Therefore, the RF-LSTM fusion algorithm significantly enhances the prediction accuracy of the 1 h PM_2.5 concentration model. As for the 2 h, 3 h, 6 h, 12 h, and 24 h PM_2.5 prediction models using the RF-LSTM fusion algorithm, their RMSEs are 5.6 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 6.9 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 9.9 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 12.6 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, and 15.3 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, and their corresponding MAPEs are 13.8%, 18.3%, 28.3%, 38.2%, and 48.2%, respectively. Their prediction accuracy decreases with longer forecasting time, but they can effectively capture the fluctuation trends of future PM_2.5 concentrations. The RF-LSTM PM_2.5 prediction models are efficient and reliable for early warning systems in Suzhou city. Full article

Malignant pleural mesothelioma (MPM) is a rare and aggressive malignancy associated with occupational or environmental exposure to asbestos. Effective management of MPM remains challenging due to its prolonged latency period and the typically late onset of clinical symptoms. Accordingly, there is an increasing demand for the implementation of reliable, non-invasive, and data-driven diagnostic strategies within large-scale screening programs. In this context, the chemical profiling of volatile organic compounds (VOCs) in exhaled breath has recently gained recognition as a promising and non-invasive approach for the early detection of cancer, including MPM. Therefore, in this cross-sectional observational study, an overall number of 125 individuals, including 64 MPM patients and 61 healthy controls (HC), were enrolled. End-tidal breath fraction (EXP) was collected directly onto two-bed adsorbent cartridges by an automated sampling system and analyzed by thermal desorption–gas chromatography–mass spectrometry (TD-GC/MS). A machine learning approach based on a random forest (RF) algorithm and trained using a 10-fold cross-validation framework was applied to experimental data, yielding remarkable results (AUC = 86%). Fifteen VOCs reflecting key metabolic alterations characteristic of MPM pathophysiology were found to be able to discriminate between MPM and HC. Moreover, twenty breath samples from asymptomatic former asbestos-exposed (AEx) and eight MPM patients during follow-up (FUMPM) were exploratively analyzed, processed, and tested as blinded samples by the validated statistical method. Good agreement was found between model output and clinical information obtained by CT. These findings underscore the potential of breath VOC analysis as a non-invasive diagnostic approach for MPM and support its feasibility for longitudinal patient and at-risk subjects monitoring. Full article

Three-dimensional bulk fin-type field-effect transistors (FinFETs) have been the dominant devices since the sub-22 nm technology node. Electrical characteristics of scaled devices suffer from different process variation effects. Owing to the trapping and de-trapping of charge carriers, random interface traps (RITs) degrade device characteristics, and, to study this effect, this work investigates the impact of RITs on the DC/AC/RF characteristic fluctuations of FinFETs. Under high gate bias, the device screening effect suppresses large fluctuations induced by RITs. In relation to different densities of interface traps (D_it), fluctuations of short-channel effects, including potential barriers and current densities, are analyzed. Bulk FinFETs exhibit entirely different variability, despite having the same number of RITs. Potential barriers are significantly altered when devices with RITs are located near the source end. An analysis and a discussion of RIT-fluctuated gate capacitances, transconductances, cut-off, and 3-dB frequencies are provided. Under high D_it conditions, we observe ~146% variation in off-state current, ~26% in threshold voltage, and large fluctuations of ~107% and ~131% in gain and cut-off frequency, respectively. The effects of the random position of RITs on both AC and RF characteristic fluctuations are also discussed and designed in three different scenarios. Across all densities of interface traps, the device with RITs near the drain end exhibits relatively minimal fluctuations in gate capacitance, voltage gain, cut-off, and 3-dB frequencies. Full article

Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality worldwide. Accurate determination of epidermal growth factor receptor (EGFR) mutation status is essential for selecting patients eligible for tyrosine kinase inhibitors (TKIs). However, invasive genotyping is often limited by tissue accessibility and sample quality. This study presents a non-invasive machine learning model combining clinical data, CT morphological features, and radiomic descriptors to predict EGFR mutation status. A retrospective cohort of 138 patients with confirmed EGFR status and pre-treatment CT scans was analyzed. Radiomic features were extracted with PyRadiomics, and feature selection applied mutual information, Spearman correlation, and wrapper-based methods. Five Random Forest models were trained with different feature sets. The best-performing model, based on 11 selected variables, achieved an AUC of 0.91 (95% CI: 0.81–1.00) under stratified five-fold cross-validation, with an accuracy of 0.88 ± 0.03. Subgroup analysis showed that EGFR-WT had a performance of precision 0.93 ± 0.04, recall 0.92 ± 0.03, F1-score 0.91 ± 0.02, and EGFR-Mutant had a performance of precision 0.76 ± 0.05, recall 0.71 ± 0.05, F1-score 0.68 ± 0.04. SHapley Additive exPlanations (SHAP) analysis identified tobacco use, enhancement pattern, and gray-level-zone entropy as key predictors. Decision curve analysis confirmed clinical utility, supporting its role as a non-invasive tool for EGFR-screening. Full article

Background: The growing interest in the field of platelet-rich fibrins has led to the development of novel generations of these concentrates, with one of the newest additions being advanced platelet-rich fibrin plus (A-PRF+). The updated centrifuge protocol utilized for the preparation of A-PRF+ has been shown to provide blood clots with more white blood cells and growth factors trapped in the fibrin matrix, presenting a more homogenous distribution. The objective of this study was to assess the available randomized clinical trials (RCTs), in order to evaluate the effects that the addition of A-PRF+ can have on postoperative quality of life and soft tissue healing after dental surgery. Materials and Methods: To perform a systematic review based on high-quality results, only RCTs were taken into consideration. The search included articles published between 1 January 2014 and 31 December 2024, indexed in the PubMed, Cochrane, Library, Embase, Scopus, and Google Scholar databases. Nine full texts were finally acquired after the screening of articles, from which relevant data were extracted. Results: A-PRF+ positively influenced the postoperative quality of life in patients. The subjective analysis of pain and its management via painkiller intake indicated that, in general, the addition of A-PRF+ into protocols results in less pain, pain that lasts for a shorter time, and pain that is more easily managed through medication, as a lower number of pills was needed to restore comfort. Furthermore, the occurrence of facial swelling and trismus was also reported to be lower in the A-PRF+ groups. As for soft tissue healing, A-PRF+ significantly enhanced the epithelialization process, total wound area reduction, and inflammation in the surrounding tissues. This positive effect was most noticeable at 7- and 14-day follow-ups. The addition of A-PRF+ also had a positive effect on postoperative bleeding by significantly reducing the bleeding time, providing benefits for patients undergoing antiplatelet drug therapy in particular. Conclusions: The addition of A-PRF+ into the surgical protocol can positively enhance the patient’s quality of life, reduce the need for postoperative medication, and improve the patient’s confidence by reducing potential swelling and trismus. A-PRF+ also positively influences soft tissue wound healing, further enhancing the postoperative well-being of patients, and provides an excellent hemostatic effect even in patients that are on antiplatelet drug therapy. Full article

Background: Despite the established importance of prescribing steroids to children with croup, many physicians in Korean emergency departments (EDs) do not adhere to this recommendation. This study aimed to evaluate treatment appropriateness by investigating steroid prescription rates and potentially low-value interventions such as salbutamol nebulizers and radiographs and to compare dedicated pediatric emergency centers (DPECs) and general emergency centers (GECs) to understand treatment trends for croup in Korea. Methods: This retrospective cohort study analyzed a 5% random sample of the National Health Screening Program for Infants and Children (NHSPIC) cohort linked to the National Health Insurance Service database (2008–2015). The study included children with a primary diagnosis of croup and excluded children who were prescribed oral or steroid injections within three days before their ED visit. The primary outcome was steroid prescription rate; secondary outcomes included comparisons of management patterns between DPECs and GECs. Results: The overall steroid prescription rate was 56.9%. Steroid prescribing was slightly higher in DPECs than in GECs (61.2% vs. 56.3%, p = 0.131). In contrast, DPECs had lower prescription rates for salbutamol nebulizers (4.5% vs. 12.7%, p < 0.001), chest radiographs (65.3% vs. 78.7%, p < 0.001), and cervical spine radiographs (4.5% vs. 12.6%, p < 0.001). Steroid prescription rates showed no significant temporal trend, while potentially low-value interventions decreased significantly. Conclusions: Only about half of children with croup in Korean EDs received steroids. DPECs were associated with lower use of potentially low-value interventions, suggesting more guideline-concordant practice. Education and implementation of standardized national croup clinical guidelines are needed to optimize care. Full article

Accurate rice yield prediction remains a major challenge due to the complex and nonlinear interactions among cultivar, environment, and phenology. Existing approaches often focus on analyzing individual components while ignoring their interdependencies, which results in limited predictive accuracy and generalizability. To overcome these problems, this study proposes a novel interpretable random forest model that integrates cultivar, environmental, and phenological dimensions. Different from conventional approaches, the proposed method incorporates a factor-combination optimization strategy to identify the most effective information for yield estimation. For analysis, 24 key determinants were screened, including the geographical location, meteorological conditions, phenological events, and cultivar traits. The RF models were also evaluated when built with seven factor combinations. The results reveal the following: (1) Meteorological conditions play a dominant role during the vegetative growth period, including net solar radiation (r = 0.42), daylength (r = 0.38), and thermal summation (r = 0.29). On the other hand, thermal summation (r = 0.28), mean minimum temperature (r = −0.23), and mean temperature (r = −0.20) are most relevant during the reproductive growth period. (2) The full-factor model achieves optimal performance (RMSE = 601.45 kg/ha and MAE = 454.98 kg/ha, R² = 0.77). (3) Importance analysis reveals that meteorological factors provide the greatest contribution (53.59%), followed by phenological factors (20.39%), geographical factors (17.20%), and cultivar (8.82%), respectively. The results also reveal that threshold effects of key determinants on yield, and identify mid-April to early May as the optimal sowing window. These findings demonstrate that integrating cultivar, environment, and phenology factors creates a powerful predictive model for rice yields. Full article

Background: Helicobacter pylori infection is associated with peptic ulcer disease, chronic gastritis, and gastric cancer. Classic triple therapy (CTT) has been widely used, but increasing antibiotic resistance has reduced its effectiveness. Objectives: To evaluate the effectiveness of CTT compared with alternative regimens and to summarize adverse events and adherence. Methods: We searched PubMed, Scopus, Web of Science, and Cochrane Library from January 2000 to March 2025. Randomized trials and observational studies assessing eradication rates were included. Two reviewers independently screened the studies, extracted data, and assessed bias using Cochrane RoB or the Newcastle–Ottawa Scale. Outcomes included eradication rate, adverse events, and adherence. Results: Thirteen studies (n = 3490) were included. CTT eradication rates ranged from 61.9% to 88.8%. Sequential, bismuth-based quadruple and high-dose PPI regimens achieved higher rates (>90% in several trials). Adverse events were mild–moderate and most frequent in quadruple therapy, though adherence remained >90%. Evidence certainty varied (moderate to low in most comparisons). Geographic variation in resistance limited generalizability. Conclusions: CTT is less effective in high-resistance regions. Quadruple, sequential, and high-dose PPI regimens provide superior outcomes. Region-specific treatment guided by susceptibility testing is recommended. Registration: Not registered. Full article

Palliative radiotherapy (PRT) is central to symptom control in advanced cancer, yet referrals are often late, and patients and clinicians frequently hold misconceptions about intent, benefits, and logistics. Patient education may address these gaps, but the PRT-specific evidence base has not been consolidated. We conducted a narrative review following SANRA guidance. We searched PubMed, Scopus, and the Cochrane Library for English-language studies from 1 January 2000 to 18 July 2025. Eligible articles evaluated structured patient-education interventions or characterized education or communication content, information needs, or decision processes among adults referred to or receiving PRT. Two reviewers independently screened and extracted data. Owing to heterogeneity of designs and endpoints, we performed a narrative synthesis without meta-analysis. Six studies met criteria: two randomized controlled trials, two prospective pre–post studies, one qualitative interview study, and one observational communication study, conducted in the Netherlands, the United States, Canada, and Hong Kong. Education at referral or consultation improved knowledge, reduced decisional uncertainty, and increased readiness to proceed with PRT. Education integrated with treatment improved symptom outcomes, including higher rates of pain control at 12 weeks and faster time to pain control when a nurse-led pain-education program accompanied PRT for painful bone metastases, and improvements in dyspnea, fatigue, anxiety, and function in advanced lung cancer. Observational and qualitative work showed low patient question-asking and persistent curative expectations; overall quality of life generally did not change. Although the evidence is limited and heterogeneous, targeted, standardized education appears to improve decision quality and selected symptoms in PRT pathways. Pragmatic multi-site trials and implementation studies are needed to define content, timing, personnel, and delivery models that are scalable in routine care. Full article