To develop and validate a machine learning model for predicting major depressive disorder (MDD) with suicidal ideation (SI) by incorporating dietary antioxidants, and to elucidate the specific contribution of these antioxidants in the prediction. Data were obtained from NHANES 2007-2010. Dietary antioxidants, including vitamins, minerals, and polyphenols, were the primary predictors. Demographic, lifestyle, and health-related variables were also included. Collinear variables were removed, class imbalance was corrected, and data were normalized prior to modeling. Twelve machine learning algorithms were compared using a systematic benchmarking protocol within the sklearn framework: Random Forest (RF), LightGBM, AdaBoost, XGBoost, Extra Trees, CatBoost, Gradient Boosting Decision Trees, Support Vector Machine, Decision Tree, Gaussian Naïve Bayes, Stochastic Gradient Descent, and K-Nearest Neighbors. SHapley Additive exPlanation (SHAP) values were calculated to interpret feature contributions within the best-performing model. A total of 9306 participants were included, of whom 247 with MDD comorbid with SI. After preprocessing, 31 dietary antioxidants and 9 demographic and health-related variables were retained for modeling. The RF classifier achieved the highest performance with an accuracy of 83%, precision of 0.825, recall of 0.838, area under the ROC curve of 0.927, and F1 score of 0.831. SHAP analysis identified vitamin C, kaempferol, myricetin, peonidin, luteolin, eriodictyol, hesperetin, pelargonidin, and zinc as the most influential predictors. The RF model exhibited superior predictive capability for comorbid MDD and SI. SHAP analysis highlighted the critical roles of dietary antioxidants, particularly vitamin C and kaempferol, in predicting these outcomes.

Prevalence of Babesia vulpes in shelter dogs from Texas, USA.

Sociodemographic variables are rarely reported in randomized controlled trials investigating posterior spinal fusion for adult spinal deformity: A systematic review.

Long-term study retention of adolescents undergoing metabolic and bariatric surgery: lessons learned from the Teen-Longitudinal Assessment of Bariatric Surgery cohort.

Integrating Reproductive and Clinical Variables to Predict Postpartum Disability Outcomes in Multiple Sclerosis Using Machine Learning.

Cutoff values of knee extensor strength for stair ascent and descent after bicruciate-stabilized total knee arthroplasty.

Trends in lumbar degenerative spine pathologies causing severe pain and disability: a four-decade cohort study of 1495 Colombian women.

Accurate survival prediction is a key component to patient quality of life (QoL)-centered treatment. It allows, for example, setting reasonable treatment goals or timely palliative care referral. However, clinical estimates are often too optimistic leading to lower patient QoL before death. Patient-reported outcomes (PROs) have proven to be an important survival predictor improving the overall prognostic accuracy. In this study, transformer architecture was explored to leverage PRO trajectories to improve survival accuracy and identify the most prognostic PRO symptoms for survival prediction. We analyzed 475 (cross-validation discovery set: 380; held-out testing set: 95) early-stage non-small cell lung cancer (NSCLC) patients who underwent SBRT treatment and routinely completed the Edmonton Symptom Assessment Scale (ESAS). A transformer-based model was developed to perform longitudinal modeling of overall survival (OS), incorporating PROs collected at multiple post-treatment follow-ups, as well as clinical and demographic variables. The performance of the proposed model was compared to traditional outcome modeling approaches, including univariate and multivariate (time-varying) Cox proportional hazards regression (CoxPH) and joint probability survival modelling. The best-performing transformer model was interpreted using the SHapley Additive exPlanation (SHAP) values, and the most prognostically relevant ESAS symptoms were identified through a backward elimination procedure guided by concordance index (c-index) and area under the ROC curve (AUC). The best-performing transformer model achieved a cross-validated c-index of 0.753 [95% CI: 0.742-0.764] and an AUC of 0.862 [95% CI: 0.846-0.878] on the discovery set. On the heldout test set, the model reached a c-index of 0.694 and an AUC of 0.785, evaluated at the last time point. It significantly outperformed both Cox models and the joint probability model. Model interpretation using SHAP values and backward elimination identified appetite loss, pain, overall well-being, and shortness of breath as the most prognostically relevant symptoms for survival prediction. Transformer-based survival models that integrate longitudinal PROs significantly enhance prognostic accuracy in SBRT-treated NSCLC patients. Loss of appetite and pain emerged as the most predictive symptoms, followed by overall wellbeing and shortness of breath. These findings suggest that targeted, symptom-focused PROs tracking could streamline clinical implementation and improve survival estimation in routine oncology care.

Associations Between Preoperative Diagnostic Tests and Surgical Recommendation for Carpal Tunnel Syndrome.

Fall risk prediction in older adults: a generalized linear mixed-effect model analysis based on physical performance measures.

Attitudinal measures of specific educational activities have been instrumental in helping educators understand the level and structure of students' attitudes. However, existing research lacks a deeper understanding of students' attitudes toward musical creative practices, particularly the nuanced interplay between cognitive, affective, and behavioral dimensions across demographic variables. To address this, our study aimed to explore three key research questions: (1) how children's cognitive, affective, and behavioral attitudes toward musical creative practice differ across age groups in terms of mean scores and distribution patterns; (2) whether there are statistically significant differences in these three dimensions across age groups; (3) whether there are statistically significant differences in these dimensions between gender groups. A self-report scale was administered to 247 elementary school students aged 7-12 from two schools in Changsha City. Data were analyzed using descriptive statistics, Kruskal-Wallis tests, and Mann-Whitney U tests. Descriptive analyses revealed that cognitive attitudes toward musical creative practice consistently scored higher than the affective and behavioral intention dimensions across all age groups. Statistical tests indicated significant differences in cognitive attitudes across age groups, while affective and behavioral intention dimensions showed no significant age-related variations. In contrast, Mann-Whitney U tests revealed significant gender differences across all three dimensions. These findings validate the tripartite structure of attitudes in the context of musical creative practice and clarify how age and gender shape these attitudes, thereby contributing to the theoretical framework and highlighting the need for tailored approaches to foster children's musical creativity.

Machine learning detecting aggression among mood disorder patients visited in psychiatric emergency departments.

Is Semaglutide a Safer Weight-Management Option Than Bariatric Surgery for Patients Undergoing Total Hip Arthroplasty (THA)?

Machine learning-based diagnostic model combined with Chinese natural language processing for surgical-site infections: development and validation.

High burden of poor prognostic factors at first presentation in treatment-naïve relapsing multiple sclerosis: Real-world evidence from a large Egyptian cohort.

Enhanced recovery after surgery protocols and the growth of minimally invasive surgery have made same-day discharge increasingly achievable in gynecologic oncology, yet implementation varies and Canadian data remain limited. We performed a retrospective cohort study of consecutive patients undergoing minimally invasive hysterectomy between 2022 and 2024 who were planned for outpatient management. Demographic and perioperative variables were collected. Failed same-day discharge was defined as unplanned postoperative admission. Descriptive and comparative statistics evaluated predictors of admission or re-admission. Of 159 minimally invasive hysterectomies, 107 (67.3%) were laparoscopic and 52 (32.7%) were robotic (32.7%). The median patient age was 60 years (IQR 52-67) and median BMI was 30.3 kg/m2 (IQR 23.8-35.4). Endometrial cancer was the most common indication (60.5%), followed by adnexal mass (29.0%) and cervical cancer (4.9%). Same-day discharge was achieved in 92.5% of patients, whereas 12 (7.5%) required overnight admission. Half of all cases were simple hysterectomies (complexity = 0), one-third involved a single additional component, and 15% had ≥2 components. Patients who failed same-day discharge had a higher BMI (median 37.0 [IQR 29.8-43.3] vs. 29.9 [IQR 23.5-35.1]; P = 0.006), were more often American Society of Anesthesiologists class 3 (50% vs. 15.6%; P = 0.011), and more frequently arrived in the postoperative care unit after 12 PM (83% vs. 45.9%; P = 0.013). Same-day discharge after minimally invasive hysterectomy was feasible in over 90% of patients, with low re-admission rates. Higher BMI and American Society of Anesthesiologists class 3 predicted failed discharge and may support preoperative counselling and pathway optimization.

Association of Metabolic Dysfunction-Associated Steatotic Liver Disease and Kidney Failure in the CKD Population

Cannabis legalization and law enforcement drug seizures: a state-level analysis of cannabis policy effects on cannabis seizures in the United States, 2010-2023.

The widespread integration of digital technologies into adolescents' daily lives has raised concerns about potential behavioral correlates, including aggression. Although prior research suggests a relationship between technology use and aggressive behavior, results are mixed and often context-dependent. This study aimed to examine the association between information technology use and aggression among Turkish adolescents. A descriptive cross-sectional study was conducted with 841 adolescents aged 11-14 years recruited from three public secondary schools in southeastern Turkey between February 3, 2025, and February 14, 2025. Data were collected using a sociodemographic questionnaire, the Information Technologies Usage Scale, and the Aggression Scale. Pearson correlation analyses and hierarchical multiple linear regression models were performed to examine associations between technology use and aggression, both before and after controlling for demographic and familial variables. Technology use was positively associated with aggression (r = 0.296, p < 0.001). In regression analyses, information technology use remained a significant predictor of aggression after adjustment for covariates (β = 0.235, p < 0.001), explaining a small proportion of variance. Among technology sub-dimensions, digital game playing and use of technological devices and applications were significantly associated with higher aggression scores, whereas virtual life preference was not. Longer daily technology use was also associated with higher aggression levels. Higher levels of technology engagement, particularly digital gaming and device use, were associated with increased aggression scores among adolescents, although the magnitude of these associations was small. Given the cross-sectional design, causal inferences cannot be drawn. The results highlight the importance of considering both the type and duration of technology use in adolescent behavioral research and underscore the need for longitudinal studies to clarify temporal relationships and underlying mechanisms.

Effects of Protein Source and Amount of Saturated Fat on Insulin Sensitivity, Insulin Secretion, and Disposition Index in Healthy Individuals.