The Hamas massacre on October 7, 2023, resulted in approximately 1,400 civilian deaths and escalated into a war between Israel and its neighbors. This conflict had a profound impact on healthcare professionals, including social workers, who faced the dual burden of addressing the needs of others while managing their own trauma. This study examined the role of personal resources and professional mission in preserving the well-being of 116 Israeli social workers operating within a war-related shared reality. Participants were recruited from three regions with differing levels of exposure: Northern Israel (relocated due to rocket attacks), Southern Israel (directly affected by the massacre and ongoing rocket fire), and Central Israel (exposed to repeated rocket alarms). Self-report questionnaires assessing psychological distress, potency, professional mission, and work-to-family conflict were administered. Findings indicated that potency and professional mission emerged as key differentiating variables in the decision tree model, highlighting their central role in shaping psychological distress outcomes during wartime. In contrast, demographic variables and family-to-work conflict served as significant predictors of psychological distress. These findings underscore the importance of internal and professional resources in mitigating psychological distress among social workers facing a war-related shared reality.

The causal effect of iterative changes in table tennis rules on the technical and tactical system: An empirical test based on Markov chain and decision tree models.

Understanding student mental health: An explainable pattern analysis approach.

To evaluate the cost-effectiveness of the Fetal Medicine Foundation (FMF) strategy, compared with the National Institute for Health and Care Excellence (NICE) strategy, for first-trimester screening for preterm preeclampsia (PE) in the United Kingdom (UK). Cost-effectiveness analysis. UK National Health Service and personal social services perspective. A total of 10 000 simulated patients with singleton pregnancies at 11-13 weeks' gestation, across a lifetime time horizon. A decision-tree model was developed to perform a cost-effectiveness analysis. In the base-case analysis, NICE-recommended screening was compared with FMF screening, using maternal factors, mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI) and placental growth factor (PlGF). The model assumed that patients identified as high-risk for PE were prescribed 150 mg aspirin daily until 36 weeks' gestation. Scenario analyses varied PE incidence, aspirin adherence and biomarker combinations of FMF strategy components. Incremental cost-effectiveness ratios (ICERs) were calculated using incremental costs and quality-adjusted life years (QALYs). Dominant ICERs demonstrated lower costs and higher QALYs. Compared with NICE-recommended screening, the FMF strategy demonstrated a cost-saving of £3191 and QALY gain of 0.92 per 10 000 patients (dominant ICER), with a cost-saving of £199 per preterm PE case avoided. In scenario analyses, the FMF strategy was cost-effective across 3%, 5% and 7% PE incidence, and 75% and 100% aspirin adherence. The base-case FMF strategy (maternal factors + MAP + UtA-PI + PlGF) was the most clinically effective option. The FMF strategy was more cost-effective versus the NICE strategy for first-trimester preterm PE screening in the UK.

Integrated molecular and clinical profiling of primary mitochondrial oxidative phosphorylation disorders in an Indian cohort: Insights from genetics, neuroimaging, and machine learning.

Cost-Utility and Budget Impact Analysis of Pharmacogenetic-Guided Antiplatelet Therapy for Acute Coronary Syndrome in Thailand.

Machine learning reveals drivers of microplastic bioaccumulation in fish from a freshwater reservoir ecosystem.

The transition to sustainable energy positions wind power as a key renewable solution. As demand grows, wind turbines are deployed across diverse terrains. However, wind’s stochastic nature and environmental variability complicate power forecasting, affecting grid stability. The study leverages data-driven techniques to enhance wind power forecasting using high-resolution SCADA system time-series data. Key operational parameters include wind speed, rotor speed, generator speed, nacelle orientation, ambient temperature and power output. A comparative analysis evaluates traditional machine learning models—Linear Regression, Decision Trees, Random Forests, Gradient Boosting and Support Vector Machines—against deep learning models like Long Short-Term Memory (LSTM) networks and a novel Recurrent Neural Network (RNN) architecture. The core contribution is an optimized Bidirectional LSTM-RNN model with permutation layers and attention. These layers capture long-range dependencies and nonlinear interactions in wind data. The structure improves long-range dependency capture and nonlinear interaction modeling. Bidirectionality enables learning from both past and future time steps, while attention mechanisms highlight critical temporal features. Experimental results demonstrate the proposed model’s superior performance, achieving a Mean Absolute Error (MAE) of 0.0994 and Root Mean Square Error (RMSE) of 0.1390, significantly outperforming traditional models (e.g., Random Forest: MAE 86.44, RMSE 220.30) and basic LSTM models (MAE 14.48, RMSE 15.27). Robust cross-validation confirms its ability to generalize across different temporal segments. Feature importance analysis improves interpretability, supporting informed decision-making in wind farm operations. The framework is scalable, modular and well-suited for real-time forecasting applications. The work presents a reliable deep learning model for wind power forecasting, enabling intelligent, data-driven energy management in modern power systems.

Explainable machine learning incorporating CHI3L1 enhances liver fibrosis staging in chronic hepatitis B: The CHILI multicenter study.

Physiological predictors of respiratory motor plasticity: A machine-learning reappraisal of phrenic motor facilitation.

Gastroparesis (GP) is a chronic gastrointestinal motility disorder that imposes a substantial clinical and economic burden. For patients with refractory GP, gastric peroral endoscopic myotomy (G-POEM) and botulinum toxin injection (BTI) are emerging therapies with differing efficacy profiles and procedural costs. Given these differences, we evaluated the cost-effectiveness of G-POEM versus BTI for refractory GP. We conducted a cost-effectiveness analysis using a decision tree model informed by randomized trial data from a US health care system perspective over 3- and 12-month time horizons. Procedural costs, adverse events, and repeat BTI sessions were incorporated. Quality-adjusted life-years (QALYs) were estimated from the Gastrointestinal Quality of Life Index (GIQLI) and from Short Form-12 (SF-12) scores. Cost-effectiveness was assessed using incremental cost-effectiveness ratios (ICERs) at a willingness-to-pay (WTP) threshold of $100,000/QALY. The base-case analysis was modeled on a 48.1-year-old patient with refractory GP-defined as persistent symptoms despite 6 months of medical therapy and a GP Cardinal Symptom Index score >2. At 3 months, G-POEM was associated with higher costs and marginally greater effectiveness than BTI (ICER $288,341/QALY), making BTI the cost-effective strategy in the short term. At 12 months, incorporating repeat BTI, G-POEM became the cost-effective option, with BTI yielding an ICER of $334,046/QALY relative to G-POEM. Sensitivity analyses identified clinical success rates and procedural costs as primary cost-effectiveness drivers. At 12 months, the cost-effectiveness acceptability curve showed G-POEM was cost-effective in most simulations at lower WTP thresholds, with BTI favored only at thresholds near $335,000/QALY. While BTI is more cost-effective in the short term, the cumulative costs of repeat sessions make G-POEM the more economically favorable strategy over 12 months. Improving clinical success rate by optimizing patient selection and refining procedural techniques could further improve cost-effectiveness profiles.

Real-time control of urban drainage system for flood and combined sewer overflow mitigation with a novel recurrent deep reinforcement learning framework.

Comparison of demographic and clinical features in adolescent-onset vs. adult-onset bipolar disorder an analysis of BIPAS Phase II data.

Understanding complex queries: Multi-query comprehension network for temporal sentence grounding

Evaluation of the Clinical Effectiveness and Cost-Effectiveness of Tirzepatide for Type 2 Diabetes in Canada Using Bayesian Transportability Analysis.

Business prospect conversion is a critical process in achieving sales performance within Business-to-Business (B2B) telecommunications services. However, many organizations experience difficulties in converting prospects into customers due to various operational constraints throughout the sales process. This study aims to identify the primary constraints affecting the conversion of business prospects into customers at Telkom Manyar Regional Office by applying the Theory of Constraints (TOC) approach. The study integrates prospect data quality measurement using Tuple Completeness and predictive analytics through a Decision Tree model. A quantitative descriptive approach was employed using 600 prospect records collected from January to June 2025. Tuple Completeness was utilized to evaluate the completeness of prospect data, while Fishbone Diagram analysis was used to identify root causes of conversion constraints. Furthermore, a Decision Tree model was developed using Altair AI Studio to predict conversion outcomes and identify influential variables. The results indicate that prospect data quality represents the primary constraint in the conversion process. Prospects with 100% Tuple Completeness achieved a conversion rate of 79.29%, while prospects with 67% and 33% completeness achieved conversion rates of 25.15% and 0%, respectively. The Decision Tree model achieved an accuracy of 86.11%, identifying Tuple Completeness as the most influential predictor of conversion success. These findings demonstrate that improving prospect data quality can significantly enhance customer conversion performance. The study contributes to the integration of Theory of Constraints, data quality assessment, and predictive analytics in the context of B2B customer acquisition within the telecommunications industry.

Detecting malicious network activity in corporate information resources using statistical traffic flow characteristics is a practically important task, since detection effectiveness is determined not only by overall accuracy but also by the ratio of false alarms to missed attacks, which directly affects the workload of security operators and the level of residual risk for an organization. This paper presents an approach to attack detection in network connection streams based on flow features using tree-based machine learning methods and analyzes their behavior across different threat classes within a single reproducible experimental protocol. The experimental study employs the CSE-CIC-IDS2018 dataset with features extracted by CICFlowMeter and formulates a binary classification problem of benign versus attack for three malicious activity scenarios covering botnet activity, volumetric DDoS attacks (HOIC, LOIC-UDP), and web attacks (Brute Force-Web, Brute Force-XSS, SQL Injection). A comparison of Decision Tree and Random Forest models is implemented with class balancing and fixed train–test split parameters to ensure a consistent evaluation across different attack types. Performance is assessed using the confusion matrix and derived metrics for the attack class, including precision and recall, as well as an analysis of absolute FP and FN values, which are most informative in the presence of rare attacks. The obtained results demonstrate an almost complete separation between benign and attack classes for Bot and DDoS, which is consistent with the presence of pronounced traffic patterns and high class separability in the feature space. For web attacks, a fundamentally different error profile is observed: the Decision Tree achieves higher detection completeness at the cost of an increased number of false alarms and reduced alert precision, whereas the Random Forest produces substantially more precise alerts while increasing the number of missed attacks. It is shown that the choice of a detection method should account for the attack type, class imbalance, and the acceptable trade-off between false alarms and missed detections, and that result interpretation should rely on metrics that reflect operational consequences for corporate network monitoring systems.

The complexity of nanoparticle toxicity necessitates applying machine learning to large toxicological datasets to identify predictive features and toxicity rules. This study investigates the relationships between the physicochemical properties of silica nanoparticles (SiNPs), external experimental parameters, and toxicity under in vitro conditions. Data from the literature, databases, and in-house experiments were balanced using our Balanced Fitted Dose–Response approach, yielding nearly equal numbers of concentration data points across toxicity levels. The CatBoost algorithm outperformed Decision Tree models in predicting SiNP toxicity. The Catboost Shapley value analysis revealed the following sequence of feature importance: Mass > Total Surface Area > Serum > Total NP Number ∼ Primary Size > Exposure Time > Chemical Surface Modification > Cell Age > Cell Culture > Cell Disease. Rule extraction from a transparent decision-tree model revealed detailed information on the interrelationships among the features of surface-modified SiNPs and their toxicity. It showed that surface-unmodified SiNPs–OH are more toxic than surface-modified SiNPs–NH2 and SiNPs–COOH. Adsorption and uptake measurements by imaging flow cytometry, employing alveolar macrophages, revealed significantly higher adsorption for SiNPs–OH compared with modified SiNPs, while uptake of SiNPs–OH was lower. The integration of computational and experimental findings suggests that adsorption of SiNPs to the macrophage membrane contributes to their toxicity, in addition to internalization, providing valuable insight into the mechanisms underlying nanoparticle safety.

Internet connectivity has significantly enhanced the efficiency of daily operations, information retrieval, and global communication. However, this heightened reliance on technology has also exposed us to cybersecurity threats that are often beyond our control. Consequently, securing the data, privacy, and critical systems demands essential cybersecurity measures. This study focuses on the role of artificial intelligence in strengthening security systems to thwart network breaches. The study proposes a comprehensive three-part approach for software-defined networking (SDN) security. The first is that the concentration is on assuring data integrity and reliability for an SDN intrusion dataset. This involves critical steps such as data cleaning, preprocessing, and normalization. In the second step, six popular feature selection strategies are applied, which encompass recursive feature elimination (RFE), polynomial features, artificial neural networks, SelectKBest, least absolute shrinkage and selection operator (LASSO), and correlation-based features. These techniques help identify and incorporate significant and relevant features, thereby improving the overall model performance. The third part involves the creation of a lightweight hybrid model (LwHM) that leverages the strengths of k-nearest neighbors and decision tree models, utilizing a voting classifier. The LwHM surpasses the performance of the InSDN dataset, achieved an impressive accuracy score of 99.93% with RFE features, and enhance the SDN security efficiently.

Aneurysmal subarachnoid hemorrhage (aSAH) is a life-threatening condition with high morbidity and mortality, particularly in poor-grade patients (World Federation of Neurosurgical Societies grades IV-V). Intraventricular hemorrhage (IVH) is associated with worse outcomes, but its predictive value and interaction with demographic and clinical factors remain unclear. To evaluate the prognostic value of IVH volume (IVHV) quantified on admission computed tomography (CT) in association with mortality and long-term disability, as well as its interaction with demographic and clinical variables in patients with poor-grade aSAH. We retrospectively analyzed all consecutive patients with poor-grade aSAH and IVH that were admitted to nine Italian tertiary centers between 1 January 2015 and 31 May 2023. Bivariate and multivariable analyses were performed to identify factors associated with mortality and disability (modified Rankin Scale [mRS]). Global intracranial hemorrhage volume (GHV) as well as the volumes of ICH (ICHV), IVH (IVHV), and SAH (SAHV) were calculated by means of analytical software in a semiautomated setting. We employed an explainable machine learning approach to examine the interplay between hemorrhage volume distribution, demographic and clinical variables to define prognostic thresholds, and to develop a decision tree model. Among 326 patients with IVH (median age 61years [IQR: 53-70], 65.6% male), IVHV was the strongest factor independently associated with mortality and disability. An IVHV threshold of 8mL optimized sensitivity and specificity for the outcome. Combining IVHV with age and ICHV further improved prognostic thresholds in the studied population; specificity was 92% for mortality and 71% sensitivity for disability. Adding IVHV to the SAFIRE scale significantly improved its predictive power (De Long p .008). IVHV is a key factor associated with mortality and disability in poor-grade aSAH with intraventricular involvement. Quantifying hemorrhage volume on admission CT is a valuable tool for improving outcome stratification and guiding clinical decision-making.