Search Results (2,275)

Autonomous Unmanned Aerial Vehicles (UAVs) are widely used in smart agriculture, logistics, and warehouse management, where precise trajectory prediction is important for safety and efficiency. Traditional approaches require complex physical modeling including mass properties, moment of inertia measurements, and aerodynamic coefficient calculations, which creates significant barriers for custom-built UAVs. Existing trajectory prediction methods are primarily designed for motion forecasting from dense historical observations, which are unsuitable for scenarios lacking historical data (e.g., takeoff phases) or requiring trajectory generation from sparse waypoint specifications (4–6 constraint points). This distinction necessitates architectural designs optimized for spatial interpolation rather than temporal extrapolation. To address these limitations, we present a segmented LSTM framework for complete autonomous flight trajectory prediction. Given target waypoints, our architecture decomposes flight operations, predicts different maneuver types, and outputs the complete trajectory, demonstrating new possibilities for mission-level trajectory planning in autonomous UAV systems. The system consists of a global duration predictor (0.124 MB) and five segment-specific trajectory generators (∼1.17 MB each), with a total size of 5.98 MB and can be deployed in various edge devices. Validated on real Crazyflie 2.1 data, our framework demonstrates high accuracy and provides reliable arrival time predictions, with an Average Displacement Error ranging from 0.0252 m to 0.1136 m. This data-driven approach avoids complex parameter configuration requirements, supports lightweight deployment in edge computing environments, and provides an effective solution for multi-UAV coordination and mission planning applications. Full article

Background: Papillary thyroid carcinoma in the isthmus (PTCI) remains a subject of surgical debate due to its unique anatomical location and reportedly more aggressive behavior, including higher rates of lymph node metastasis, multifocality, extrathyroidal extension, and capsular invasion. There are currently no definitive guidelines regarding the optimal extent of surgery. Objective: This study aimed to compare the three surgical approaches—total thyroidectomy, lobectomy with isthmusectomy, and isthmusectomy/extended isthmusectomy—in patients with PTCI, focusing on postoperative complications, tumor recurrence, recovery, and identifying risk factors for tumor prognosis and lymph node metastasis. Methods: We retrospectively analyzed data from 215 patients treated surgically across four medical centers from 2016 to 2022, divided into three groups based on surgical extent. We compared baseline characteristics, operative time, intraoperative blood loss, length of hospital stay, postoperative complications, and central lymph node metastasis risk factors. Propensity Score Matching (PSM) was used to create more comparable groups, so as to verify the accuracy and stability of our research results. Results: No significant differences were observed among the three groups in rates of temporary or permanent recurrent laryngeal nerve injury, permanent hypoparathyroidism, or chyle leakage (all p > 0.05). However, transient hypoparathyroidism was more common in the total thyroidectomy group (p < 0.05), which also had longer operative time, greater intraoperative blood loss, and longer postoperative hospital stay (all p < 0.05) The PSM-adjusted analyses further confirmed these findings, except that the previously observed difference in postoperative drainage volume among the three groups was no longer significant (p = 0.791). The Kaplan–Meier curves showed a similar cumulative proportion of recurrence-free survivors in the three groups with no statistically significant difference observed (p = 0.804). Univariate and multivariate logistic regression analysis identified that gender (OR = 4.405, 95%CI: 4.104–4.729, p < 0.001), multifocality (OR = 2.498, 95%CI: 1.064–5.864, p = 0.035), tumor diameter (OR = 1.096, 95%CI: 1.047–1.147, p < 0.001), capsular invasion (OR = 2.666, 95%CI: 2.547–2.791, p < 0.001), and absolute eosinophil count (OR = 1.381, 95%CI: 1.125–1.695, p = 0.002) remained significant independent predictors of central lymph node metastasis in PTCI. A multivariable logistic regression model was developed to predict CLNM, achieving an AUC of 0.777. A probability threshold of 0.50 provided the best balance between sensitivity (77.6%) and specificity (65.5%) and was selected as the clinical cut-off for stratifying high- and low-risk patients. Conclusions: Conservative procedures like lobectomy with isthmusectomy or isthmusectomy/extended isthmusectomy may represent a feasible, function-preserving option in carefully selected low-risk PTCI patients, but further validation is required. In contrast, patients with high-risk features may benefit from central lymph node dissection. The predictive model may provide supportive information for personalized surgical planning. Full article

ST-elevation myocardial infarction (STEMI) remains a major health concern despite advances in care. Indoxyl sulfate (IS) and p-cresyl-sulfate (p-CS) are gut-derived uremic toxins linked to higher morbidity and mortality in patients with chronic kidney disease (CKD). IS has been identified as an independent predictor of major adverse cardiovascular events (MACE) after STEMI, but data on p-CS are lacking. This study assessed the predictive value of IS and p-CS in STEMI patients with preserved renal function (cohort # NCT03070496). Plasma IS and p-CS were measured in 260 patients with STEMI who underwent primary coronary angiography. Samples collected 4 h after inclusion were analyzed using ultra-performance liquid chromatography with fluorescence detection. Optimal cut-offs were determined by the Youden index, and associations with MACE were evaluated by log-rank tests and Cox regression. Among 234 analyzed patients, 11.5% experienced MACE within one year. IS and p-CS levels were higher in the MACE group (IS: 3.14 vs. 2.19 µmol/L, p < 0.05; p-CS: 6.76 vs. 2.70 µmol/L, p < 0.01). Elevated p-CS independently predicted MACE (HR 3.79, 95% CI 1.29–11.17, p < 0.05), whereas IS lost significance after adjusting for kidney function. In STEMI patients, plasma p-CS is a stronger independent predictor of MACE than IS, highlighting its potential role in the gut–heart axis. Full article

Background/Objective: Hypertension is a major global health concern and a leading cause of cardiovascular morbidity and mortality. Lifestyle behaviors, such as diet, physical activity, stress management, and self-confidence, markedly influence hypertension control. Exploring these behaviors can inform culturally relevant interventions for improving the prevention and management of hypertension and health outcomes of affected individuals. This study aimed to determine the effects of lifestyle behaviors, including dietary habits, physical activity, stress management, and self-confidence, on optimizing hypertension control among individuals in Saudi Arabia. Methods: A cross-sectional, descriptive–correlational design was used. Data were collected from 136 patients with hypertension attending primary healthcare centers in Saudi Arabia using validated scales for dietary habits, physical activity, perceived stress, and self-confidence, alongside blood pressure measurements. Data were analyzed using Statistical Package for the Social Sciences version 26. Results: The study revealed that most participants reported reasonably healthy dietary practices, low physical activity, and moderate stress and self-confidence. Significant sex differences (p < 0.05) were observed, with men and women reporting higher physical activity and stress, respectively. Education and age influenced dietary habits and self-confidence. Regression analysis identified age, education, and urban residence as predictors (p < 0.05) of blood pressure status, while stress, diet, and physical activity affected self-confidence and perceived stress levels. Conclusions: Hypertension management is influenced by interconnected lifestyle and psychosocial factors, and improving dietary habits, physical activity, stress management, and self-confidence is essential. Tailored interventions addressing demographic differences can enhance self-care behaviors and facilitate better hypertension control among Saudi individuals. Full article

Background: Pediatric craniofacial fractures represent a distinct clinical entity characterized by unique anatomical and developmental factors that differentiate them from adult facial trauma. Despite their relative rarity, these injuries pose diagnostic and therapeutic challenges due to the presence of active growth centers and the potential for long-term functional and esthetic sequelae. Methods: A retrospective observational study was conducted among pediatric patients aged 0–17 years treated for craniofacial fractures between 2020 and 2024 at the Department of Cranio-Maxillofacial Surgery, University Hospital in Kraków, Poland. Demographic data, injury mechanisms, fracture distribution, treatment modality, and associated injuries were analyzed. Multivariate logistic regression was applied to identify predictors of surgical intervention. Results: Ninety-eight patients met the inclusion criteria. The mean age was 12 years, with a male predominance. Midfacial fractures were most common, with orbital floor fractures representing the single most frequent injury. Surgical management was performed in 72 cases, predominantly using the transconjunctival approach and autologous bone grafting. Orbital floor fractures were identified as the only independent predictor of operative treatment (p < 0.05). Central nervous system trauma was the most frequent concomitant injury. No significant changes in etiology or fracture distribution were observed during the COVID-19 pandemic. Conclusions: Pediatric craniofacial trauma follows a reproducible, age- and mechanism-dependent pattern. Effective management requires individualized, growth-preserving, and function-oriented treatment strategies. Standardization of care protocols and multicenter prospective studies are essential to optimize outcomes and develop evidence-based, age-specific guidelines for the management and prevention of pediatric facial fractures. Full article

Acellular dermal matrices (ADMs) are widely used in soft-tissue reconstruction, yet the optimal timing for split-thickness skin grafting (STSG) remains unsettled. We conducted a single-center retrospective cohort study (January 2023–August 2025) of adults undergoing ADM-based reconstruction with Integra^® Double Layer (IDL), Integra^® Single Layer (ISL), or Nevelia^®. Primary endpoints included length of stay (LOS), STSG requirement and timing, and in-hospital complications; secondary endpoints included spontaneous epithelialization. Prespecified adjusted analyses (linear/logistic models) controlled for age, sex, etiology, anatomical site, diabetes/PAOD, smoking, wound size (when available), wound contamination, and matrix type. Histology and immunohistochemistry (H&E, Masson trichrome, CD105, D2-40) assessed matrix integration and vascular/lymphatic maturation. Seventy-five patients were included (IDL n = 40; ISL n = 20; Nevelia n = 15). On multivariable analysis, matrix type was not an independent predictor of LOS (ISL vs. IDL β = +2.84 days, 95% CI −17.34 to +23.02; Nevelia vs. IDL β = −4.49 days, 95% CI −16.24 to +7.26). Complications were infrequent (6/75, 8.0%) and comparable across matrices; spontaneous epithelialization occurred in 3/75 patients (4.0%). A day-14 grafting strategy, applied only after documented clinical integration, was feasible in 30/75 (40.0%) patients without excess complications. Histology/IHC at 3–4 weeks demonstrated CD105-positive, perfused capillary networks with abundant collagen; at 4–6 weeks, D2-40-positive lymphatic structures confirmed progressive neo-dermis maturation, supporting the biological plausibility of earlier grafting once integration criteria are met. In this cohort, outcomes were broadly similar across matrices after adjustment. A criteria-based early STSG approach (~day 14) appears safe and operationally advantageous when integration is confirmed, while a minority of defects may heal without grafting. Prospective multicenter studies with standardized scar/functional measures and cost analyses are needed to refine patient selection and graft timing strategies. Full article

Objective: In this study, we aimed to determine the most significant risk factors for 5-year mortality in patients with paroxysmal and persistent drug-refractory tachysystolic atrial fibrillation after undergoing atrioventricular node ablation (AVNA) in combination with the implantation of a permanent three-chamber pacemaker with an implantable cardioverter–defibrillator function (CRT-D). Methods: This prospective single-center cohort study included 101 patients with chronic heart failure (mean age 62 ± 15.5 years; 70.3% male) with paroxysmal or persistent drug-refractory atrial fibrillation who underwent atrioventricular node ablation and CRT-D implantation. All patients received optimal medical therapy before and after undergoing the procedure. Predictors of 5-year mortality were assessed using exploratory machine-learning methods, including random forest and Shapley additive explanations. Results: During 5-year follow-up, 13 cardiovascular deaths were recorded. Five key predictors of mortality were identified: left ventricular ejection fraction, 6 min walk distance, mean pulmonary artery pressure, systolic relaxation coefficient, and degree of mitral regurgitation. The exploratory predictive model showed high accuracy (92%) in terms of classifying the outcomes. Conclusions: Atrioventricular node ablation (AVNA) combined with CRT-D was associated with the observed long-term clinical outcomes observed in patients with drug-refractory tachysystolic atrial fibrillation. The exploratory machine learning analysis identified key mortality-associated factors, which may support future efforts in personalized risk stratification and hypothesis generation. The combination of AVNA and CRT-D was associated with the observed long-term outcomes in this real-world cohort. Full article

Background/Objectives: The extent of myocardial scar, visualized by late gadolinium enhancement (LGE) on cardiac magnetic resonance imaging (CMR), is associated with mortality after acute myocardial infarction (MI). However, data on optimal cardiac biomarker cut-off values (e.g., high-sensitivity cardiac troponin T, hs-cTnT) for predicting LGE remain limited. This study aimed to evaluate the predictive value of cardiac biomarkers for LGE and their influence on clinical outcomes. Methods: We included 597 patients who underwent CMR a median of 3 days [interquartile range (IQR) 2–4 days] after MI (407 STEMI and 190 NSTEMI patients), with a median follow-up period of 3.0 years [IQR 1.3–3.5 years]. Results: After adjusting for key variables, maximum cardiac biomarker levels were found to have the strongest correlation with the presence and extent of LGE (p < 0.001). LGE mass and LVEF were the most robust predictors of all-cause mortality (hazard ratio [CI] 1.464 [1.050–2.040], p = 0.025, Harrell’s C 0.812; 0.697 [0.491–0.990], p = 0.044, Harrell’s C 0.810, respectively). We determined a receiver operating characteristic (ROC) area under the curve (AUC) of 0.73 and an optimal cut-off of 53 g for LGE mass and mortality, with a maximum hs-cTnT cut-off of 7270 ng/L predicting this extent of LGE. Conclusions: In this large cohort of MI patients with three-year follow-up, cardiac biomarker levels showed a strong correlation with the extent of LGE. While absolute LGE mass was associated with mortality, its predictive value was comparable to that of CMR-derived LVEF. These findings should be interpreted cautiously, given the study’s observational design, and should be considered hypothesis-generating, underscoring the need for prospective validation. Full article

Soil salinization is an escalating global concern threatening agricultural productivity and ecological sustainability, particularly in coastal regions where complex interactions among hydrological, climatic, and anthropogenic factors govern salt accumulation. The vertical differentiation and spatial heterogeneity of salinity drivers remain poorly resolved. We present an integrated modeling framework combining ensemble machine learning and spatial statistics to investigate the depth-specific dynamics of soil salinity in the Yellow River Delta, a vulnerable coastal agroecosystem. Using multi-source environmental predictors and 220 field samples harmonized to 30 m resolution, the hybrid Gray Wolf Optimizer–Random Forest–XGBoost model achieved high predictive accuracy for surface salinity (R² = 0.91, RMSE = 0.03 g/kg, MAE = 0.02 g/kg). Spatial autocorrelation analysis (Global Moran’s I = 0.25, p < 0.01) revealed pronounced clustering of high-salinity hotspots associated with seawater intrusion pathways and capillary rise. The results reveal distinct vertical control mechanisms: vegetation indices and soil water content dominate surface salinity, while total dissolved solids (TDS), pH, and groundwater depth increasingly influence middle and deep layers. By applying SHAP (SHapley Additive Explanations), we quantified nonlinear feature contributions and ranked key predictors across layers, offering mechanistic insights beyond conventional correlation. Our findings highlight the importance of depth-specific monitoring and intervention strategies and demonstrate how explainable machine learning can bridge the gap between black-box prediction and process understanding. This framework offers a generalizable framework that can be adapted to other coastal agroecosystems with similar hydro-environmental conditions. Full article

Background: Monitoring training load and recovery is essential for performance optimization and injury prevention in youth football. However, predicting subjective recovery in preadolescent athletes remains challenging due to biological variability and the multidimensional nature of training responses. This exploratory study examined whether supervised machine learning (ML) models could predict Total Quality of Recovery (TQR) using integrated external load, internal load, anthropometric and maturational variables collected over one competitive microcycle. Methods: Forty male sub-elite U11 and U13 football players (age 10.3 ± 0.7 years; height 1.43 ± 0.08 m; body mass 38.6 ± 6.2 kg; BMI 18.7 ± 2.1 kg/m²) completed a microcycle comprising four training sessions (MD-4 to MD-1) and one official match (MD). A total of 158 performance-related variables were extracted, including external load (GPS-derived metrics), internal load (RPE and sRPE), heart rate indicators (U13 only), anthropometric and maturational measures, and tactical–cognitive indices (FUT-SAT). After preprocessing and aggregation at the player level, five supervised ML algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Gradient Boosting (GB)—were trained using a 70/30 train–test split and 5-fold cross-validation to classify TQR into Low, Moderate, and High categories. Results: Tree-based models (DT, GB) demonstrated the highest predictive performance, whereas linear and distance-based approaches (SVM, KNN) showed lower discriminative ability. Anthropometric and maturational factors emerged as the most influential predictors of TQR, with external and internal load contributing modestly. Predictive accuracy was moderate, reflecting the developmental variability characteristics of this age group. Conclusions: Using combined physiological, mechanical, and maturational data, these ML-based monitoring systems can simulate subjective recovery in young football players, offering potential as decision-support tools in youth sub-elite football and encouraging a more holistic and individualized approach to training and recovery management. Full article

Accurate wind information is essential for safe and efficient port operations, yet many small and medium-sized coastal ports lack dense meteorological instrumentation. This paper presents a data-driven framework for wind speed prediction at such ports by leveraging long-term historical measurements from nearby reference stations. Focusing on a real-world case study at the Chalkida port in Greece, the framework integrates both deterministic and Machine Learning (ML) models trained on historical wind patterns of archived wind data from four surrounding locations. We examine both short- and long-horizon prediction periods, using recently acquired wind measurements at the target port for model validation. Deterministic baselines include simple and weighted averaging schemes, while supervised ML methods, such as Multiple Linear Regression, Decision Trees, Support Vector Regression, Random Forests, and Gradient Boosting, are trained to capture complex spatiotemporal patterns. Experimental results highlight that ensemble-based ML models, particularly Gradient Boosting, achieve superior accuracy in short-term forecasting, while the optimal predictor varies with the forecast horizon. The proposed approach enables the deployment of virtual wind stations in data-scarce ports and can be periodically updated to dynamically select the most suitable model, thereby supporting climate adaptation strategies, localized wind monitoring, and operational planning without requiring dense local instrumentation. Full article

Background: Tyrosine kinase inhibitors (TKIs) have transformed the prognosis of chronic myeloid leukemia (CML), but pediatric patients face unique challenges due to prolonged exposure. Early molecular response (EMR, BCR::ABL1 ≤ 10% at 3 months) is a recognized predictor of favorable outcomes in adults and has been correlated with improved responses in children. However, its relationship with achieving deep molecular remission (DMR, BCR::ABL1 ≤ 0.01%) in pediatric CML remains unclear. Methods: We performed a single-center, retrospective analysis of 103 pediatric patients with chronic-phase CML treated with frontline TKIs. Among them, 88 were evaluable for molecular response. BCR::ABL1 transcript levels were quantified by real-time quantitative PCR on the International Scale, and molecular responses were assessed. Associations between early molecular dynamics and long-term outcomes were evaluated using Kaplan–Meier and cumulative incidence analyses. Results: At 3 months, 64.8% achieved EMR. Early responders had significantly higher MMR rates at 12 months (80.8% vs. 5.6%; p = 0.00018) and DMR at 24 months (70.4% vs. 42.2%; p = 0.029). The ≥0.45-log reduction in BCR::ABL1 transcripts at 3 months predicted shorter times to MMR (median 11 vs. 29 months) and DMR (18 vs. 50 months), as well as higher overall MMR (p = 0.011) and DMR (p = 0.014) incidences. Bone marrow fibrosis correlated with inferior molecular outcomes (p = 0.017 for MMR). Conclusions: Early BCR::ABL1 decline kinetics independently predict molecular depth in pediatric CML. Quantitative early transcript reduction may guide risk-adapted management and optimize long-term TKI strategies in children. Full article

Background: The importance of integrating enhanced recovery after surgery protocols in gynecologic oncology has been proven in numerous studies. However, the actual adherence to protocol among institutions remains inconsistent in clinical practice, particularly among those without prior structured implementation. This pragmatic multicenter study provides a preliminary report from the ongoing ERGO (Enhanced Recovery in Gynecologic Oncology) cohort study (ClinicalTrials.gov: NCT06655506) and aims to evaluate adherence to enhanced recovery protocols during the early phases of its adoption as well as identify factors that determine low uptake. Methods: Overall, 300 consecutive patients undergoing gynecologic oncology surgery across five institutions were included in the present study. Adherence to preoperative, intraoperative, and postoperative enhanced recovery elements was documented using standardized forms. Optimal adherence was predetermined as fulfillment of more than 70% of the enhanced recovery components included in the pathway. Multinomial analysis was used to identify predictors of adherence. Results: Overall, 70.3% of patients achieved optimal adherence; however, rates varied across centers (26.9–84.4%), reflecting the limited institutional familiarity with enhanced recovery pathways in most participating centers. The actual volume of cases handled was an important determinant of adherence, with high-volume units consistently demonstrating substantially higher compliance compared with lower-volume hospitals. Routine preoperative items demonstrated high uptake, whereas several intraoperative and early postoperative components showed low and heterogeneous implementation, which might be the result of anesthesiology-driven practices. Higher surgical complexity and poorer performance status independently predicted reduced adherence. Visual mapping confirmed that complex procedures resulted in lower adherence. Conclusions: The significant variability in enhanced recovery protocol adherence that was observed in our study indicates the need to institute structured workflows that help increase team familiarization, particularly in high-complexity cases and centers new to these elements. Full article

Background: Idiopathic sudden sensorineural hearing loss (ISSNHL) is an abrupt unilateral hearing loss of unknown origin. Combination therapy with hyperbaric oxygen (HBO), systemic steroids (SS), and prostaglandin E1 (PGE1) has been used in Japan; however, its prognostic factors remain unclear. Objective: To evaluate the efficacy of HBO combined with SS and PGE1 and to identify prognostic factors for hearing recovery in patients with ISSNHL. Methods: This retrospective study included 116 patients treated within 14 days of ISSNHL onset. Sixty patients received HBO, SS, and PGE1 (HBO group), and 56 received SS and PGE1 alone (No-HBO group). Hearing outcomes were assessed using PTA (arithmetic mean hearing at 250–4000 Hz) and graded by Siegel’s criteria. Prognostic factors were analyzed by multivariate logistic regression. Results: The HBO group showed significantly better hearing grade outcomes (p = 0.007) and greater PTA improvement (p = 0.003) than the No-HBO group. Vertigo and higher initial PTA were identified as independent predictors of poor hearing outcomes. Patients without vertigo showed significantly greater improvement at 2000 Hz (p = 0.009). Receiver operating characteristic analysis revealed an optimal initial PTA cutoff of ≥90.5 dB for predicting poor hearing outcome. Conclusions: HBO combined with SS and PGE1 significantly improves hearing outcomes in ISSNHL. However, the presence of vertigo and severe initial hearing loss remain poor prognostic indicators. These findings suggest that while the addition of HBO may enhance hearing outcomes, prognosis remains limited in severe cases. Further prospective studies are needed to confirm these results. Full article

Background: Approximately one quarter of community-dwelling older adults experience at least one fall each year. Falls can result in soft tissue injuries, fractures, or even death. Given this high prevalence, it is essential to identify fall-related risk factors, develop predictive models, and prescribe effective exercise-based interventions to prevent falls. Objective: To analyze risk factors, predictors, and therapeutic interventions for falls in older adults. Methods: A literature search was conducted in SCIELO, PUBMED, and PEDro databases between 15–20 October 2025. Inclusion criteria comprised peer-reviewed, open-access studies in English published from 2020 onward. Findings were categorized into three domains: (1) fall risk factors, (2) predictive models, and (3) exercise-based interventions. Twenty studies met the inclusion criteria. Results: Falls among older adults arise from multifactorial interactions involving physical, clinical, cognitive, and social factors such as impaired mobility, comorbidities, polypharmacy, and cognitive decline. Lower-limb strength and functional performance are key determinants of fall risk. Current predictive models show limited accuracy, with fall history as the strongest predictor. Exercise-based interventions, particularly multicomponent and home-based programs, improve balance, strength, and mobility but show variable effects on fall rates. The absence of standardized parameters for exercise prescription limits the development of evidence-based guidelines. Conclusions: Falls in older adults are multifactorial events influenced by physical and cognitive decline. Predictive models remain imprecise, and although exercise interventions improve functional outcomes, their impact on reducing falls is inconsistent. Standardized exercise protocols are needed to optimize fall prevention strategies. Full article