Search Results (285)

Despite the agricultural sector’s consistently high injury rates, formal reporting is often limited, leading to sparse national datasets that hinder effective safety interventions. To address this, our study introduces a comprehensive framework leveraging advanced ensemble machine learning (ML) models to predict and interpret the severity of agricultural injuries. We use a unique, manually curated dataset of over 2400 agricultural incidents from AgInjuryNews, a public repository of news reports detailing incidents across the United States. We evaluated six ensemble models, including Gradient Boosting (GB), eXtreme Grading Boosting (XGB), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Histogram-based Gradient Boosting Regression Trees (HistGBRT), and Random Forest (RF), for their accuracy in classifying injury outcomes as fatal or non-fatal. A key contribution of our work is the novel integration of explainable artificial intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), to overcome the “black-box” nature of complex ensemble models. The models demonstrated strong predictive performance, with most achieving an accuracy of approximately 0.71 and an F1-score of 0.81. Through global SHAP analysis, we identified key factors influencing injury severity across the dataset, such as the presence of helmet use, victim age, and the type of injury agent. Additionally, our application of local SHAP analysis revealed how specific variables like location and the victim’s role can have varying impacts depending on the context of the incident. These findings provide actionable, context-aware insights for developing targeted policy and safety interventions for a range of stakeholders, from first responders to policymakers, offering a powerful tool for a more proactive approach to agricultural safety. Full article

Due to its abundance, bird cherry–oat aphid is the most important vector in Poland of the complex of viruses causing barley yellow dwarf virus (BYDV). These viruses infect all cereals. During the growing season, cereal plants are exposed to many species of agrophages, which can limit their growth, development and yield. As observed for many years, global warming contributes to changes in the development of many organisms. Aphids (Aphidoidea), which are among the most important pests of agricultural crops, respond very dynamically to these changes. Under favorable conditions, their populations can increase several-fold within a few days. The bird cherry–oat aphid (Rhopalosiphum padi L.) is a dioecious species that undergoes a seasonal host shift during its life cycle. Its primary hosts are trees and shrubs (Prunus padus L.), while secondary hosts include cereals and various grass species. R. padi feeds directly on bird cherry tree, reducing its ornamental value, and on cereals, where it contributes to yields losses. The species can also damage plants indirectly by transmitting harmful viruses. Indirect damage is generally more serious than direct feeding injury. Monitoring aphid flights with a Johnson suction trap (JST) is useful for plant protection, which enables early detection of their presence in the air and then on cereal crops. To provide early detection of R. padi migrations and to study the dynamics of abundance, flights were monitored in 2020–2024 with Johnson suction traps at two localities: Winna Góra (Greater Poland Province) and Sośnicowice (Silesia Province). The aim of the research conducted in 2020–2024 was to study the dynamics of the bird cherry–oat aphid (Rhopalosiphum padi L.) population in relation to meteorological conditions as recorded by a Johnson suction trap. Over five years of research, a total of 129,638 R. padi individuals were captured using a Johnson suction trap at two locations (60,426 in Winna Góra and 69,212 in Sośnicowice). In Winna Góra, the annual counts were as follows: 5766 in 2020, 6498 in 2021, 36,452 in 2022, 5598 in 2023, and 6112 in 2024. In Sośnicowice, the numbers were as follows: 6954 in 2020, 9159 in 2021, 49,120 in 2022, 3855 in 2023, and 124 in 2024. The year 2022 was particularly notable for the exceptionally high abundance of R. padi, especially in the autumn. Monitoring crops for the presence of pests is the basis of integrated plant protection. Climate change, modern cultivation technologies, and increasing restrictions on chemical control are the main factors contributing to the development and spread of aphids. Therefore, measures based on monitoring the level of threat and searching for control solutions are necessary. Full article

Objective: To develop and validate an interpretable deep learning model based on the TabNet architecture for predicting doxorubicin-induced cardiotoxicity (DIC) in patients with breast cancer through integration of multidimensional clinical data. Methods: This retrospective study included 2034 patients who received doxorubicin-based chemotherapy at The Fourth Affiliated Hospital of Harbin Medical University between January 2021 and December 2023. Clinical, biochemical, electrocardiographic, and echocardiographic parameters were incorporated into six predictive algorithms: logistic regression, decision tree, random forest, gradient boosting machine, XGBoost, and TabNet. Model discrimination, calibration, and clinical utility were assessed using AUC, C-index, calibration plots, and decision curve analysis. Model interpretability was evaluated through attention-based feature importance and SHAP analysis. Results: TabNet achieved the best overall predictive performance, with an AUC of 0.86 and a C-index of 0.80 in the validation cohort, demonstrating superior discrimination, calibration, and generalization compared with all baseline models. Decision curve analysis confirmed its higher net clinical benefit across threshold probabilities. The model identified eight dominant predictors—cumulative anthracycline dose, LVEF, QTc interval, lactate dehydrogenase, creatinine, glucose, hypertension, and platelet count—that collectively reflected myocardial contractility, electrophysiological stability, and systemic metabolic stress. Correlation and clustering analyses revealed that high-risk patients exhibited concurrent QTc prolongation, metabolic disturbance, and LVEF decline, defining a distinct cardiometabolic injury phenotype. These findings highlight TabNet’s ability to uncover complex feature interactions while maintaining transparent and clinically interpretable outputs. Conclusions: The TabNet-based multidimensional model provides an accurate, stable, and interpretable tool for individualized prediction of doxorubicin-induced cardiotoxicity, supporting early intervention and precision management in breast cancer patients receiving anthracycline therapy. Full article

Secular trees have an important contribution to today’s communities, not only due to cultural or historical reasons but also to recreational aspects. Management of such species can be done after a thorough analysis is done related to their health status. In most cases, a visual inspection to determine the health status can lead to unsatisfactory results. Modern technology, such as computer tomography, has results that are accurate and valid. A total of 17 secular oak trees (Quercus robur) were sampled and analyzed with Arbotom 2D (Arbotom 2D, Rinn Tech, Heidelberg, Germany) by using sensors on the tree trunks. Besides this, it is imperative to compare the results in the field with the view of the community related to their local symbol. Results revealed severe internal decay (75%–80% damaged wood) in eight oaks, while in the core of the trunk (10%–50% damaged wood), it was seen in seven oaks. Only two oaks have good health status. Survey results indicated the oaks as moderate healthy; only 18.8% respondents from the community consider the oaks unhealthy or in visible decline. This can lead to serious injuries to bystanders. The results have demonstrated a great link between technical and social research so decision-making stakeholders can apply a tailored management for their area. Full article

Background/Objectives: The Manchester Colour Wheel (MCW) was developed as an alternative way of assessing health status, mood and treatment outcomes. There has been a dearth of research on this alternative assessment approach. The present study examines the sensitivity of the MCW to pain, psychological factors and recovery status in 1098 people with insured injuries treated in an interdisciplinary clinic. Methods: A deidentified data set of clients treated in a multidisciplinary clinic was conveyed to the researchers, containing results of MCW and injury-specific psychometric tests at intake, as well as recovery status at discharge. Systematic machine modelling was applied. Results: There were no significant differences between the four injury types studied: motor crash-related Whiplash Associated Disorder (WAD) and workplace-related Shoulder Injury (SI), Back Injury (BI) and Neck Injury (NI) on the MCW. Augmenting the MCW with Machine Learning (ML) models showed overall classification rates for Classification and Regression Tree (CRT) of 75.6% for Anxiety, 70.3% classified for Depression and 68.5% for Stress, and Quick Unbiased Efficient Statistical Trees could identify 68.5% of Pain Catastrophisation and 62.7% of Kinesiophobia. Combining MCW with psychometric measurements markedly increased the predictive power, with a CRT model predicting WAD recovery status with 80.7% accuracy, SI recovery status 81.7% accuracy and BI recovery status with 78% accuracy. A Naïve Bayes Classifier predicted recovery status in NI with 96.4% accuracy. However, this likely represents overfitting. Conclusions: Overall, MCW augmented with ML offers a promising alternative to questionnaires, and the MCW appears to measure some unique psychological features that contribute to recovery from injury. 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

This study presents a comprehensive statewide analysis of pedestrian-involved crashes recorded in Tennessee between 2002 and 2025. We evaluated the influence of roadway, traffic, environmental, and socioeconomic factors on pedestrian crash frequency and severity with substantial components focused on lighting impacts including dark and nighttime. A multi-method analytical framework was implemented, combining descriptive statistics, non-parametric tests, regression analysis, and advanced machine learning techniques including the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the gradient boosting model (XGBoost). Results indicated that dark and nighttime conditions accounted for a disproportionate share of severe crashes—fatal and serious injuries under dark conditions reached over 40%, compared to less than 20% during daylight. The statistical tests revealed statistically significant differences in both total injuries and fatalities between low-speed (≤35 mph) and higher-speed (40–45 mph) corridors. The regression result identified AADT and the number of lanes as the strongest predictors of crash frequency, showing that greater traffic exposure and wider cross-sections substantially elevate pedestrian risk, while terrain and peak-hour traffic exhibited negative associations with severe injuries. The XGBoost model, consisting of 300 trees, achieved R² = 0.857, in which the SHAP analysis revealed that AADT, the roadway functional class, and the number of lanes are the most influential variables. The ANFIS model demonstrated that areas with higher population density and greater proportions of households without vehicles experience more pedestrian crashes. These findings collectively establish how pedestrian crash risks are correlated with traffic exposure, roadway geometry, lighting, and socioeconomic conditions, providing a strong analytical foundation for data-driven safety interventions and policy development. Full article

Cold winter injury is a significant challenge in cultivating tropical trees in temperate regions. The conventional solution involves heating the entire greenhouse to protect the plants; however, this approach is fuel-intensive and costly. This study investigated whether root-zone heating can mitigate cold injury in coffee trees. In the Control, non-heated treatments, leaf relative water content dropped to approximately 70%, leading to wilting, whereas in the Heat treatment, it remained above 90%. In the Control treatment, defoliation progressed, ultimately resulting in more than 50% leaf loss. In contrast, defoliation was reduced by approximately 20% with the Heat treatment. During the cold-treatment period, photosynthesis declined sharply in both the Control and Heat treatments, with CO₂ assimilation dropping to nearly zero. However, one week after the complete of cold treatment, F_v/F_m recovered to pre-treatment levels, while CO₂ assimilation and electron transport rates improved to more than 50% of pre-treatment levels in the Heat treatment. These findings indicate that root-zone heating helps prevent leaf wilting and defoliation by maintaining high leaf water content. The surviving leaves recovered their photosynthetic function and were crucial in subsequent biomass production. Thus, root-zone heating is a cost-effective and efficient strategy for cultivating tropical trees in temperate regions. Full article

Background: Muscle injuries are among the main problems in professional soccer, affecting player availability and team performance. Countermovement jump (CMJ) variables have been proposed as indicators of injury risk and for detecting strength imbalances, although their use is less explored than isokinetic assessments. Unlike previous studies based solely on linear statistics, this research integrates biomechanical data with machine learning approaches, providing a novel perspective for injury prediction in elite soccer. Objective: To examine the association between CMJ variables and muscle injury risk during a competitive season, considering injury incidence and effective playing minutes. It was hypothesized that specific CMJ asymmetries would be associated with a higher injury risk, and that machine learning algorithms could accurately classify players according to their injury status. Methods: Forty-one professional soccer players (18 women, 23 men) from national league teams (Chile) were assessed during preseason using force platforms. Non-contact muscle injuries and playing minutes were recorded over 10 months after the CMJ evaluations. Analyses included two-way ANOVA (sex × injury status) and machine learning algorithms (Logistic Regression, Decision Tree, K-Nearest Neighbors [KNN], Random Forest, Gradient Boosting [GB]). Results: Significant sex differences were observed in most variables (p < 0.05 and η_p² > 0.11), except peak force and peak power asymmetry. For injury status, only peak force asymmetry differed, while sex × injury interactions were found in peak power and left peak power. KNN (Accuracy = 87% and CI 95% = 71% to 96%) and GB (Accuracy = 84% and CI 95% = 68% to 94%) achieved the best classification performance between injured and non-injured players. Conclusions: CMJ did not show consistent statistical differences between injured and non-injured groups. However, machine learning models, particularly KNN and GB, demonstrated high predictive accuracy, suggesting that injuries are a complex phenomenon characterized by non-linear patterns. These findings highlight the potential of combining CMJ with machine learning approaches for functional monitoring and early detection of injury risk, though validation in larger cohorts is required before establishing clinical thresholds and preventive applications. Full article

In general, epilepsy is considered to be one of most prevalent neurological disorders and frequently appears as sudden seizures resulting in injuries, accidents, sudden unexpected death, etc. Also, it is reported that around 60 million people across the globe are experiencing various seizures due to epilepsy. So, there is demand for ambulatory seizure detection devices to prevent such accidents and to improve the quality of life for epilepsy patients. In this work, an intelligent Internet of Medical Things (IoMT)-based wearable device is designed and developed to monitor seizures in epilepsy patients. Due to the lack of an accelerometer dataset for epileptic seizures, the proposed device was developed, and a dataset mimicking seizure-like activities was generated. Further, the proposed device utilizes an MPU6500-based inertial measurement unit (IMU) which is integrated into an ESP32 microcontroller board. The ESP32 has a built-in wireless fidelity (WiFi) + Bluetooth (BLE) un that supports MicroPython v1.22.1 programming. Also, the machine learning algorithms such as Decision Trees (DT), Support Vector Machines (SVM), and Random Forest (RF) were programmed using MicroPython v1.22.1 programming and deployed on a tiny edge computing device to monitor the activity of the epileptic patients. All the adopted machine learning algorithms were compared in terms of performance metrics such as accuracy, precision, recall, false positive rate (FPR), etc., and the efficacy of the device was analysed. Results demonstrate that the proposed device is capable of identifying the activities of individuals, which is highly useful for epilepsy patients to monitor epileptic seizures. Furthermore, the proposed device was deployed with an RF algorithm since it exhibits an accuracy of 95% which is better compared to other machine learning algorithms. Also, the proposed device is simple and cost-effective and, in the event of a seizure event, can alert caretakers of epilepsy patients with an FPR of less than 4%. Full article

Construction sites present intrinsically hazardous conditions characterized by dynamic and complex operational environments which persistently contribute to elevated rates of occupational injuries. While conventional safety management emphasizes controls during the execution phase, addressing safety considerations during the earliest phases of a project is more effective. In this work, a Nonlinear Multifactor Safety Index (NMF-SI) is developed to quantify activity-level occupational risk for use in project planning. The index synthesizes multiple risk factors, including accident probability, task severity, exposure duration, workforce size, and contextual variables, such as weekday effects, and site conditions, like waste accumulation. Additionally, it incorporates a structured questionnaire to capture the implementation of safety measures on site. Its nonlinear formulation reflects interactions among factors, penalizes temporal clustering of high-risk tasks, and prioritizes temporal distribution and proactive planning. To produce risk-aware schedules, a hybrid optimization framework that couples a tree-based constructive heuristic with the marine predators algorithm is introduced, maximizing NMF-SI subject to project-duration, precedence, and resource constraints. In simulation, the optimized schedules achieve higher NMF-SI values and a smoother risk profile over time than baseline plans. These results translate into a quantitative, data-driven contribution to safety by design, offering a practical decision-support tool for intelligent, risk-aware construction scheduling. Full article

The increasing use of artificial intelligence (AI) in athlete health monitoring and injury prediction presents both technological opportunities and complex ethical challenges. This narrative review critically examines 24 empirical and conceptual studies focused on AI-driven injury forecasting systems across diverse sports disciplines, including professional, collegiate, youth, and Paralympic contexts. Applying an IMRAD framework, the analysis identifies five dominant ethical concerns: privacy and data protection, algorithmic fairness, informed consent, athlete autonomy, and long-term data governance. While studies commonly report the effectiveness of AI models—such as those employing decision trees, neural networks, and explainability tools like SHAP and HiPrCAM—few offers robust ethical safeguards or athlete-centered governance structures. Power asymmetries persist between athletes and institutions, with limited recognition of data ownership, transparency, and the right to contest predictive outputs. The findings highlight that ethical risks vary by sport type and competitive level, underscoring the need for sport-specific frameworks. Recommendations include establishing enforceable data rights, participatory oversight mechanisms, and regulatory protections to ensure that AI systems align with principles of fairness, transparency, and athlete agency. Without such frameworks, the integration of AI in sports medicine risks reinforcing structural inequalities and undermining the autonomy of those it intends to support. Full article

The growing implementation of close-to-nature forestry practices in the management of northern forests, characterized by dispersed harvesting operations, has heightened the importance of minimizing damage to residual stands as a key aspect of sustainable forest management. The objective of this study is to examine and compare the resistance of various tree species and diameter classes to wounds incurred during logging operations of differing sizes, intensities, and locations. In addition, the research aims to assess temporal changes in wound characteristics, including healing and closure processes, across species. This long-term, 18-year investigation was conducted in the Kheyrud Forest, located within the Hyrcanian broadleaf forest region of northern Iran, to evaluate the dynamics of wound healing in residual trees following ground-based skidding operations. Through a comprehensive assessment of 272 wounded trees across six species, we demonstrate that species significantly influences healing ratio (Kruskal–Wallis, p < 0.01), with Oriental beech (Fagus orientalis Lipsky) (50.6%) showing superior recovery compared to the Chestnut-leaved oak (Quercus castaneifolia) (37.5%). Healing ratio decreased with larger diameter at breast height (DBH) (R² = 0.114, p < 0.01), while absolute healed area increased. Larger areas (>1000 cm²) reduced healing by 42.3% versus small wounds (<500 cm²) (R² = 0.417, p < 0.01). Severe wounds (deep gouges) showed 19% less healing than superficial injuries (p = 0.003). Circular wounds healed significantly better than rectangular forms (χ² = 24.92, p < 0.001). Healing ratio accelerated after the first decade, reaching 69% by year 17 (R² = 0.469, p < 0.01). Wound height (p = 0.117) and traffic intensity (p = 0.65) showed no statistical impact. Contrary to expectations, stem position had no significant effect on wound recovery, whereas wound geometry proved to be a critical determinant. The findings highlight that appropriate species selection, minimizing wound size (to less than 500 cm²), and adopting extended cutting cycles (exceeding 15 years) are essential for enhancing residual stand recovery in close-to-nature forestry systems. Full article

This article presents a novel statistical approach for analyzing occupational accident data from the ESAW database, aiming to improve the evaluation and prediction of accident severity among specific groups of employees. The proposed method combines univariate and multivariate analytical techniques (effect size measures and classification tree methods: CHAID and CART) to identify employee groups that are both statistically robust and meaningfully distinct. The resulting model is based on six key variables describing employee and workplace characteristics, enabling accurate prediction of accident severity within these groups. The model demonstrates high reliability in predicting accident severity, achieving over 80% accuracy in a binary classification (high vs. low risk), making it a valuable tool for risk management and proactive safety planning. The findings have both theoretical and practical implications. Theoretically, the model’s strong predictive performance suggests that accident severity is not random but follows identifiable patterns linked to underlying risk factors that go beyond standard occupational or economic classification. Practically, the model allows for a more detail and effective categorization of work environments into high- and low-risk classes, and can support safety professionals, managers, and policymakers in achieving more precise identification of employee groups that are more prone to severe accidents. Full article

Background: The use of resuscitative endovascular balloon occlusion of the aorta (REBOA) for control of noncompressible torso hemorrhage remains controversial. We aimed to utilize a novel and transparent/interpretable artificial intelligence (AI) method called Optimal Policy Trees (OPTs) to improve the appropriate use and decrease the misuse of REBOA in hemodynamically unstable blunt trauma patients. Methods: We trained and then validated OPTs that “prescribe” REBOA in a 50:50 split on all hemorrhagic shock blunt trauma patients in the 2010–2019 ACS-TQIP database based on rates of survival. Hemorrhagic shock was defined as a systolic blood pressure ≤90 on arrival or a transfusion requirement of ≥4 units of blood in the first 4 h of presentation. The expected 24 h mortality rate following OPT prescription was compared to the observed 24 h mortality rate in patients who were or were not treated with REBOA. Results: Out of 4.5 million patients, 100,615 were included, and 803 underwent REBOA. REBOA patients had a higher rate of pelvic fracture, femur fracture, hemothorax, pneumothorax, and thoracic aorta injury (p < 0.001). The 24 h mortality rate for the REBOA vs. non-REBOA group was 47% vs. 21%, respectively (p < 0.001). OPTs resulted in an 18% reduction in 24 h mortality for REBOA and a 0.8% reduction in non-REBOA patients. We specifically divert the misuse of REBOA by recommending against REBOA in cases where it leads to worse outcomes. Conclusions: This proof-of-concept study shows that interpretable AI models can improve mortality in unstable blunt trauma patients by optimizing the use and decreasing the misuse of REBOA. To date, these models have been used to predict outcomes, but their groundbreaking use will be in prescribing interventions and changing outcomes. Full article