Search Results (314)

Background: Nonadherence to antihypertensive therapy affects nearly half of treated patients worldwide, and persistence often falls below 60% within the first year, contributing substantially to uncontrolled blood pressure and cardiovascular morbidity. Adherence and persistence to antihypertensive therapy among primary care patients in Mureș County, Romania, were assessed using validated measures, and modifiable risk factors for targeted interventions were identified. Methods: A cross-sectional study of 399 hypertensive adults (≥18 years) receiving treatment for ≥1 year across primary care clinics in Mureș County, Romania, was performed. Adherence was evaluated using the Romanian-validated Hill–Bone Compliance to High Blood Pressure Therapy Scale (HBCTS) and confirmed by mean arterial pressure (MAP) < 100 mmHg. Receiver operating characteristic (ROC) curve analysis was employed to determine the optimal HBCTS cutoff, and multivariate logistic regression was used to identify independent predictors of adherence. Persistence was assessed via healthcare-engagement metrics over a 360-day observation period. Results: Effective blood pressure control (MAP < 100 mmHg) was achieved by 45.9% of participants. The HBCTS demonstrated good reliability (McDonald’s ω = 0.82). ROC analysis established 51 points as an optimal threshold (sensitivity = 88.0%, specificity = 38.9%). Male gender (OR = 0.47, 95% CI: 0.29–0.75, p = 0.002) and younger age (OR = 1.04 per year, 95% CI: 1.01–1.06, p = 0.001) independently predicted poor adherence. Treatment coverage days showed the strongest correlation with blood pressure control (r = −0.50, p < 0.001). Among participants, 67.7% demonstrated persistence, achieving significantly better blood pressure control than non-persistent patients. Conclusions: The validated HBCTS (≥51 points) provides an efficient screening tool for Romanian primary care settings. Treatment coverage days emerged as the strongest modifiable predictor of blood pressure control (r = −0.50), highlighting medication availability as a key intervention target. Targeted approaches for male and younger patients, combined with systematic medication continuity monitoring, represent evidence-based strategies for reducing cardiovascular morbidity in this population. Full article

This article presents a comprehensive assessment of mudflow risk in the Talgar River basin through the application of Multi-Criteria Decision Analysis (MCDA) methods and numerical modeling using the Rapid Mass Movement Simulation (RAMMS) environment. The first part of the study involves a spatial assessment of mudflow hazard and susceptibility using GIS technologies and MCDA. The key condition for evaluating mudflow hazard is the identification of factors influencing the formation of mudflows. The susceptibility assessment was based on viewing the area as an object of spatial and functional analysis, enabling determination of its susceptibility to mudflow impacts across geomorphological zones: initiation, transformation, and accumulation. Relevant criteria were selected for analysis, each assigned weights based on expert judgment and the Analytic Hierarchy Process (AHP). The results include maps of potential mudflow hazard and susceptibility, showing areas of hazard occurrence and risk impact zones within the Talgar River basin. According to the mudflow hazard map, more than 50% of the basin area is classified as having a moderate hazard level, while 28.4% is subject to high hazard, and only 1.8% falls under the very high hazard category. The remaining areas are categorized as very low (4.1%) and low (14.7%) hazard zones. In terms of susceptibility to mudflows, 40.1% of the territory is exposed to a high level of susceptibility, 35.6% to a moderate level, and 5.5% to a very high level. The remaining areas are classified as very low (1.8%) and low (15.6%) susceptibility zones. The predictive performance was evaluated through Receiver Operating Characteristic (ROC) curves, and the Area Under the Curve (AUC) value of the mudflow hazard assessment is 0.86, which indicates good adaptability and relatively high accuracy, while the AUC value for assessing the susceptibility of the territory is 0.71, which means that the accuracy of assessing the susceptibility of territories to mudflows is within the acceptable level of model accuracy. To refine the spatial risk assessment, mudflow modeling was conducted under three scenarios of glacial-moraine lake outburst using the RAMMS model. For each scenario, key flow parameters—height and velocity—were identified, forming the basis for classification of zones by impact intensity. The integration of MCDA and RAMMS results produced a final mudflow risk map reflecting both the likelihood of occurrence and the extent of potential damage. The presented approach demonstrates the effectiveness of combining GIS analysis, MCDA, and physically-based modeling for comprehensive natural hazard assessment and can be applied to other mountainous regions with high mudflow activity. Full article

Accurate forecasting of river siltation is essential for ensuring inland waterway navigability and guiding sustainable sediment management. This study investigates the downstream reach of the Shihutang navigation power hub along the Ganjiang River in Jiangxi Province, China, an area characterized by pronounced seasonal sedimentation and hydrological variability. To enable fine-scale prediction, we developed a data-driven framework using a random forest regression model that integrates high-resolution bathymetric surveys with hydrological and meteorological observations. Based on the field data from April to July 2024, the model was trained to forecast monthly siltation volumes at a 30 m grid scale over a six-month horizon (July–December 2024). The results revealed a marked increase in siltation from July to September, followed by a decline during the winter months. The accumulation of sediment, combined with falling water levels, was found to significantly reduce the channel depth and width, particularly in the upstream sections, posing a potential risk to navigation safety. This study presents an initial, yet promising attempt to apply machine learning for spatially explicit siltation prediction in data-constrained river systems. The proposed framework provides a practical tool for early warning, targeted dredging, and adaptive channel management. Full article

Background/Objectives: Traumatic brain injury (TBI), especially mild TBI (mTBI), is frequently caused by traffic accidents, falls, or sports injuries. Although computed tomography (CT) is the gold standard for diagnosis, overuse can lead to unnecessary radiation exposure, increased healthcare costs, and emergency department saturation. Blood-based biomarkers have emerged as potential tools to optimize CT scan use. This systematic review aims to evaluate recent evidence on the role of specific blood biomarkers in guiding CT decisions in patients with mTBI. Methods: A systematic search was conducted in the PubMed, Cochrane, and CINAHL databases for studies published between 2020 and 2024. Inclusion criteria focused on adult patients with mTBI evaluated using both CT imaging and at least one of the following biomarkers: glial fibrillary acidic protein (GFAP), ubiquitin carboxy-terminal hydrolase L1 (UCH-L1), and S100 calcium-binding protein B (S100B). After screening, six studies were included in the final review. Results: All included studies reported high sensitivity and negative predictive value for the selected biomarkers in detecting clinically relevant intracranial lesions. GFAP and UCH-L1, particularly in combination, consistently identified low-risk patients who could potentially forgo CT scans. While S100B also showed high sensitivity, discrepancies in cutoff values across studies highlighted the need for harmonization. Conclusions: Blood biomarkers such as GFAP, UCH-L1, and S100B demonstrate strong potential to reduce unnecessary CT imaging in mTBI by identifying patients at low risk of significant brain injury. Future research should focus on standardizing biomarker thresholds and validating protocols to support their integration into clinical practice guidelines. Full article

Background: Unlike most cancers, breast cancer poses a persistent risk of distant recurrence—often years after initial treatment—making long-term risk stratification uniquely challenging. Current tools fall short in predicting late metastatic events, particularly for early-stage patients. Methods: We present an interpretable machine learning (ML) pipeline to predict distant recurrence-free survival at 5, 10, and 15 years, integrating Bayesian network-based causal feature selection, deep feed-forward neural network models (DNMs), and SHAP-based interpretation. Using electronic health record (EHR)-based clinical data from over 6000 patients, we first applied the Markov blanket and interactive risk factor learner (MBIL) to identify minimally sufficient predictor subsets. These were then used to train optimized DNM classifiers, with hyperparameters tuned via grid search and benchmarked against models from 10 traditional ML methods and models trained using all predictors. Results: Our best models achieved area under the curve (AUC) scores of 0.79, 0.83, and 0.89 for 5-, 10-, and 15-year predictions, respectively—substantially outperforming baselines. MBIL reduced input dimensionality by over 80% without sacrificing accuracy. Importantly, MBIL-selected features (e.g., nodal status, hormone receptor expression, tumor size) overlapped strongly with top SHAP contributors, reinforcing interpretability. Calibration plots further demonstrated close agreement between predicted probabilities and observed recurrence rates. The percentage performance improvement due to grid search ranged from 25.3% to 60%. Conclusions: This study demonstrates that combining causal selection, deep learning, and grid search improves prediction accuracy, transparency, and calibration for long-horizon breast cancer recurrence risk. The proposed framework is well-positioned for clinical use, especially to guide long-term follow-up and therapy decisions in early-stage patients. Full article

Background/Objectives: Falls in hospitalized pediatric patients are frequent and can lead to serious complications and increased healthcare costs. Nurses typically assess fall risk using structured tools such as the Humpty Dumpty Fall Scale (HDFS), alongside nursing diagnoses such as Fall risk ND, which are based on clinical reasoning. However, the degree of alignment between the HDFS and the nursing reasoning-based diagnostic approach in assessing fall risk remains unclear. This study aims to assess the alignment between the HDFS and Fall risk ND in identifying fall risk among hospitalized pediatric patients. Methods: A retrospective observational study was conducted in a tertiary pediatric hospital in Italy, including all pediatric patients admitted in 2022. Fall risk was assessed within 24 h from hospital admission using two approaches, the HDFS (risk identified with the standard cutoff, score ≥ 12) and Fall risk ND, based on the nurse’s clinical reasoning and recorded through the PAIped clinical nursing information system. Discriminative performance was analyzed using receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. A confusion matrix evaluated classification performance at the cutoff (≥12). Results: Among 2086 inpatients, 80.9% had a recorded Fall risk ND. Of the 1853 patients assessed with the HDFS, 52.7% were classified as at risk (HDFS score ≥ 12). The HDFS showed low discriminative ability in detecting patients with a Fall risk ND (AUC = 0.568; 95% CI: 0.535−0.602). The PPV was high (85.1%), meaning that most patients identified as at risk by the HDFS were also judged to be at risk by nurses through Fall risk ND. However, the NPV was low (20.1%), indicating that many patients with low HDFS scores were still diagnosed with Fall risk ND by nurses. Conclusions: The HDFS shows limited ability to discriminate pediatric patients with Fall risk ND, capturing a risk profile that does not fully align with nursing clinical reasoning. This suggests that standardized tools and clinical reasoning address distinct yet complementary dimensions of fall risk assessment. Integrating the HDFS into a structured nursing diagnostic process—guided by clinical expertise and supported by continuous education—can strengthen the effectiveness of fall prevention strategies and enhance patient safety in pediatric settings. Full article

This study, in response to the optimization needs of fall risks for the elderly in the context of cultural and tourism integration in Hebei Province, China, established a quantitative correlation system between ten gait parameters and ten types of spatial risk factors. By collecting gait data (Qualisys infrared motion capture system, sampling rate 200 Hz) and spatial parameters from 30 elderly subjects (with mild, moderate, and severe functional impairments), a multi-level regression model was established. This study revealed that step frequency, step width, and step length were nonlinearly associated with corridor length, door opening width, and step depth (R² = 0.53–0.68). Step speed, ankle dorsiflexion, and foot pressure were key predictive factors (OR = 0.04–8.58, p < 0.001), driving the optimization of core spatial factors such as threshold height, handrail density, and friction coefficient. Step length, cycle, knee angle, and lumbar moment, respectively, affected bed height (45–60 cm), switch height (1.2–1.4 m), stair riser height (≤35 mm), and sink height adjustment range (0.7–0.9 m). The prediction accuracy of the ten optimized values reached 86.7% (95% CI: 82.1–90.3%), with Hosmer–Lemeshow goodness-of-fit x² = 7.32 (p = 0.412) and ROC curve AUC = 0.912. Empirical evidence shows that the graded optimization scheme reduced the fall risk by 42–85%, and the estimated fall incidence rate decreased by 67% after the renovation. The study of the “abnormal gait—spatial threshold—graded optimization” quantitative residential layout optimization provides a systematic solution for the data-quantified model of elderly-friendly residential renovations. Full article

Background: Prehabilitation programs improve postoperative outcomes in vulnerable patients undergoing major surgery. However, current screening tools such as the Malnutrition Universal Screening Tool (MUST) may lack the sensitivity needed to identify those who would benefit most. Muscle quality assessed by Computed Tomography (CT), specifically muscle radiodensity in Hounsfield Units (HUs), has emerged as a promising alternative for risk stratification. Objective: To evaluate the prognostic performance of CT-derived muscle radiodensity in predicting adverse postoperative outcomes in colorectal cancer patients, and to compare it with the performance of the MUST score. Methods: This single-center cross-sectional study included 201 patients with non-metastatic colon cancer undergoing elective laparoscopic resection. Patients were stratified based on enrollment in a multimodal prehabilitation program, either within an Enhanced Recovery After Surgery (ERAS) protocol or a non-ERAS pathway. Nutritional status was assessed using MUST, SARC-F questionnaire (strength, assistance with walking, rise from a chair, climb stairs, and falls), and the Global Leadership Initiative on Malnutrition (GLIM) criteria. CT scans at the L3 level were analyzed using automated segmentation to extract muscle area and radiodensity. Postoperative complications and hospital stay were compared across nutritional screening tools and CT-derived metrics. Results: MUST shows limited sensitivity (<27%) for predicting complications and prolonged hospitalization. In contrast, CT-derived muscle radiodensity demonstrates higher discriminative power (AUC 0.62–0.69), especially using a 37 HU threshold. In the non-ERAS group, patients with HU ≤ 37 had significantly more complications (33% vs. 15%, p = 0.036), longer surgeries, and more severe events (Clavien–Dindo ≥ 3). Conclusions: Opportunistic CT-based assessment of muscle radiodensity outperforms traditional screening tools in identifying patients at risk of poor postoperative outcomes, and may enhance patient selection for prehabilitation strategies like the ERAS program. Full article

Background/Objectives: The objective of this study was to validate the Spanish version of the European Evaluation of Vertigo (EEV) and analyse its test–retest reliability, standard error of measurement (SEM), minimum detectable change (MDC), concurrent validity, and discriminant validity. Methods: A cross-sectional validation study was designed. Subjects were recruited from the Otolaryngology Service of the University Hospital of Jaen. Psychometric properties of the EEV were analysed, including the concurrent validity, the SEM, and the MDC. Discriminant validity was calculated using the receiver operating characteristic (ROC) curve. Results: The EEV test–retest reliability was nearly perfect (Kappa index = 0.97). The SEM and the MDC were set at 0.56 and 1.10, respectively. Regarding the discriminant validity, the area under the curve (AUC) was 0.831 (95% CI; 0.743–0.899) for the BPPV prediction, the AUC = 0.731 (95% CI; 0.633–0.815) for the disability prediction from the ABC-16 score, and the AUC = 0.846 (95% CI; 0.760–0.911) for the disability prediction from the ABC-6 score. Furthermore, a cut-off point greater than 12 was a good predictor of disability and the fall risk measured with the ABC scale, whereas a value of 11 points was a good predictor for discriminating BPPV patients. Conclusions: The Spanish version of the EEV is a valid and reliable instrument for evaluating the clinical symptoms of vestibular syndrome. This instrument demonstrated a nearly perfect test-retest reliability, a low measurement error, and good accuracy in discriminating between patients with vestibular disorders and those with BPPV. Full article

Background: Falls are a major public health concern among older adults, often resulting in injury, functional decline, and reduced quality of life. While handgrip strength (HGS), fall efficacy, and balance confidence have individually been associated with fall risk, their combined predictive value is still underexplored, particularly in physically active older adults. This study aimed to investigate the relationship between HGS, fall efficacy, and balance confidence and their association with fall risk in community-dwelling older adults engaged in regular exercise programs; A cross-sectional study was conducted with 280 participants aged 55 and over from community exercise programs near Lisbon, Portugal. Fall risk was assessed through self-reported falls in the past 12 months. HGS was measured with a dynamometer, fall efficacy using the Falls Efficacy Scale-International (FES-I), and balance confidence using the Activities-specific Balance Confidence (ABC) Scale. Statistical analyses included Spearman correlations and binary logistic regression. Results: Falls were reported by 26.4% of participants. Fall efficacy and balance confidence were significantly associated with fall history, while HGS was not. Fall efficacy was significantly associated with increased fall risk, as indicated by the odds ratio (OR = 3.37, p < 0.001), while balance confidence was negatively associated (OR = 0.95, p < 0.001). HGS was positively correlated with balance and confidence but not with fall incidence. Conclusions: Psychological factors, particularly fall efficacy and balance confidence, play a critical role in fall risk among physically active older adults. However, this study included physically active middle-aged and older adults living in the community, which should be considered when interpreting the generalizability of the results. These findings support the integration of simple, validated psychological assessments into fall prevention strategies in community settings. Full article

Objectives: To identify cognitive domains predictive of dynamic balance performance in older adults and inform targeted cognitive-motor interventions aimed at improving balance and reducing fall risk. Methods: This cross-sectional study used hierarchical multiple regression to analyze relationships between cognitive domains and dynamic balance among 62 community-dwelling older adults (≥65 years). Balance was assessed using the Y Balance Test (YBT) and Timed Up and Go Test (TUG), while cognitive function was measured using the Mini-Mental State Examination (global cognition), Stroop Test (inhibition), N-back Test (working memory), and Deary–Liewald Reaction Time Test (processing speed). Statistical analyses were conducted using SPSS, version 28, with significance set at p < 0.05. Results: Although all cognitive domains correlated with dynamic balance, regression analyses indicated that only global cognition and inhibition were significant predictors. Specifically, global cognition significantly predicted both TUG and YBT performance, whereas inhibition uniquely predicted YBT performance (all p < 0.05). Conclusions: Our findings suggest global cognition and inhibition are key cognitive predictors of dynamic balance in older adults. Assessing these domains could identify individuals at risk of impaired balance, facilitating the design of targeted, personalized cognitive-motor interventions. Future research should investigate cognitively enriched exercise programs, including digital therapeutics and wearable technologies, to effectively target these cognitive domains, enhance balance outcomes, and promote sustained physical activity adherence in aging populations. Full article

This study aims to enhance the accuracy and interpretability of flood susceptibility mapping (FSM) in Seoul, South Korea, by integrating automated machine learning (AutoML) with explainable artificial intelligence (XAI) techniques. Ten topographic and environmental conditioning factors were selected as model inputs. We first employed the Tree-based Pipeline Optimization Tool (TPOT), an evolutionary AutoML algorithm, to construct baseline ensemble models using Gradient Boosting (GB), Random Forest (RF), and XGBoost (XGB). These models were further fine-tuned using Bayesian optimization via Optuna. To interpret the model outcomes, SHAP (SHapley Additive exPlanations) was applied to analyze both the global and local contributions of each factor. The SHAP analysis revealed that lower elevation, slope, and stream distance, as well as higher stream density and built-up areas, were the most influential factors contributing to flood susceptibility. Moreover, interactions between these factors, such as built-up areas located on gentle slopes near streams, further intensified flood risk. The susceptibility maps were reclassified into five categories (very low to very high), and the GB model identified that approximately 15.047% of the study area falls under very-high-flood-risk zones. Among the models, the GB classifier achieved the highest performance, followed by XGB and RF. The proposed framework, which integrates TPOT, Optuna, and SHAP within an XAI pipeline, not only improves predictive capability but also offers transparent insights into feature behavior and model logic. These findings support more robust and interpretable flood risk assessments for effective disaster management in urban areas. Full article

Older adults make up about 12% of the public sector, primary care, and hospital use and represent a large proportion of the users of healthcare services. Older people are also more vulnerable to serious injury from unexpected falls due to tripping, slipping, or illness. This underscores the immediate necessity of stable and cost-effective e-health technologies in maintaining independent living. Artificial intelligence (AI) and machine learning (ML) offer promising solutions for early fall prediction and continuous health monitoring. This paper introduces a novel cooperative AI model that forecasts the risk of future falls in the elderly based on behavioral and health abnormalities. Two AI models’ predictions are combined to produce accurate predictions: The ${AI}_1$ model is based on vital signs using Fuzzy Logic, and the ${AI}_2$ model is based on Activities of Daily Living (ADLs) using a Deep Belief Network (DBN). A meta-model then combines the outputs to generate a total fall risk prediction. The results show 85.71% sensitivity, 100% specificity, and 90.00% prediction accuracy when compared to the Morse Falls Scale (MFS). This emphasizes how deep learning-based cooperative systems can improve well-being for older adults living alone, facilitate more precise fall risk assessment, and improve preventive care. Full article

Background: Falls are common among individuals with multiple sclerosis (MS), yet standard clinical mobility assessments—such as the Timed Up and Go (TUG)—may not fully capture the complexities of real-world ambulation, leading to suboptimal fall identification. There is a critical need to evaluate the ecological validity of these assessments and identify alternative tests that better reflect real-world mobility and more accurately detect falls. This study examined the ecological validity of the TUG and novel dual-task clinical assessments by comparing laboratory-based gait metrics to community ambulation in individuals with MS and evaluated their ability to identify fallers. Methods: Twenty-seven individuals with MS (age 59.11 ± 10.57) completed the TUG test and three novel dual-task mobility assessments (TUG-extended, 25-foot walk and turn, and Figure 8 walk), each performed concurrently with a phonemic verbal fluency task. After lab assessments, the participants wore accelerometers for three consecutive days. Gait speed and stride regularity data was collected during both the in-lab clinical assessments and identified walking bouts in the community. The participants were stratified as fallers or non-fallers based on self-reported fall history over the previous six months. Findings: Significant differences were observed between the TUG and real-world ambulation for both gait speed (p < 0.01) and stride regularity (p = 0.04). No significant differences were found in gait metrics between real-world ambulation and both the 25-foot walk and turn and TUG-extended. Intraclass correlation coefficient analysis demonstrated good agreement between the 25-foot walk and turn and real-world ambulation for both gait speed (ICC = 0.75) and stride regularity (ICC = 0.81). When comparing the TUG to real-world ambulation, moderate agreement was observed for gait speed (ICC = 0.56) and poor agreement for stride regularity (ICC = 0.41). The 25-foot walk and turn exhibited superior predictive ability of fall status (AUC = 0.76) compared to the TUG (AUC = 0.67). Conclusions: The 25-foot walk and turn demonstrated strong ecological validity. It also exhibited superior predictive ability of fall status compared to the TUG. These findings support the 25-foot walk and turn as a promising tool for assessing mobility and fall risk in MS, warranting further study. Full article

Accurate corporate credit ratings are essential for financial risk assessment; yet, traditional methodologies relying on manual evaluation and basic statistical models often fall short in dynamic economic conditions. This study investigated the potential of machine-learning (ML) algorithms as a more precise and adaptable alternative for credit rating predictions. Using a seven-year dataset from S&P Capital IQ Pro, corporate credit ratings across 20 countries were analyzed, leveraging 51 financial and business risk variables. The study evaluated multiple ML models, including Logistic Regression, Support Vector Machines, Decision Trees, Random Forest, Gradient Boosting (GB), and Neural Networks, using rigorous data pre-processing, feature selection, and validation techniques. Results indicate that Artificial Neural Networks (ANN) and GB consistently outperform traditional models, particularly in capturing non-linear relationships and complex interactions among predictive factors. This study advances financial risk management by demonstrating the efficacy of ML-driven credit rating systems, offering a more accurate, efficient, and scalable solution. Additionally, it provides practical insights for financial institutions aiming to enhance their risk assessment frameworks. Future research should explore alternative data sources, real-time analytics, and model explainability to facilitate regulatory adoption. Full article