The noninvasive diagnosis of pancreatic lesions is a critical clinical challenge. This study aims to create machine learning (ML) radiomic models for differentiating pancreatic lesions and an integrated model for pancreatic ductal adenocarcinoma (PDAC) detection.
640 patients with pathologically confirmed malignant (n = 450), borderline (n = 108), or benign (n = 82) lesions were enrolled and divided into training (70%) and validation (30%) cohorts. Radiomic features were extracted from regions of interest on arterial and venous phase CT scans. LASSO logistic regression was used to select 36 features for building ML models, including random forest, logistic regression, support vector machine, and artificial neural networks. An integrated nomogram combining radiomic features and CA19-9 levels was developed to distinguish PDAC from borderline tumors. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis.
All ML models effectively differentiated the three tumor types. The random forest algorithm showed the best performance, achieving an area under the curve (AUC) of 0.99 and 0.95 in the training and validation sets, respectively. CA19-9 was identified as an independent diagnostic factor for PDAC. The nomogram integrating radiomics and CA19-9 achieved an AUC of 0.89 and accuracy of 0.85 in the training set, with corresponding values of 0.85 and 0.82 in the validation set.
Radiomics-based ML models effectively differentiated benign, borderline, and malignant pancreatic tumors. The nomogram combining radiomic features with CA19-9 demonstrated robust performance, showing considerable potential to streamline the diagnostic process and facilitate timely care planning for patients with suspected pancreatic cancer.
Chemotherapy-related information needs are crucial for patient-centered care, yet their specific domains remain uncharacterized, particularly lacking large-scale, high-quality evidence from real-world clinical communication contexts.
The current study used the “Haodf.com” Internet-based consultation platform. Consultation records of 3000 breast cancer patients were obtained using province-stratified random sampling with proportional allocation. Using BERTopic modeling and structured data input methods, basic information and chemotherapy-related information needs of patients were identified. Chi-square tests and binary logistic regression were used to examine associations between patients’ clinical and demographic characteristics and each information need.
BERTopic modeling initially delineated 10 information need topics; manual structured data entry and validation subsequently uncovered an additional 11 latent needs, resulting in a final taxonomy of 21 need categories. The study enrolled 2781 valid consultation records, from which an average of 2.11 chemotherapy-related information needs were extracted per record. “Treatment options available,” “benefits and risks of chemotherapy,” “problems of side effects of chemotherapy drugs,” and “current stage of disease and test results” were the top-ranked information needs. Different information needs were identified and differentiated across specific dimensions, including gender, age, disease metastasis, illness duration, treatment stage, and frequency of interactions.
By creating a quantifiable map of information needs related to breast cancer chemotherapy, the current study established an evidence-based framework for the creation of precise, patient-centered, and dynamically adjusted interventional care.
This study aims to examine nurses’ views on positive clinical work environments integrated with their religious beliefs and to determine their metaphors.
The study population consisted of nurses working in a university hospital in eastern Turkey between May 6 and 16, 2025. The study sample consisted of 41 nurses who agreed to participate. The criterion sampling method was used. The research data were collected using the “Introductory Information Form” and “Semistructured Questionnaire.” Content analysis was used to evaluate qualitative data, and descriptive statistical methods (frequency, percentage, and mean) were used to evaluate quantitative data. This study followed the COREQ checklist.
The analysis of data obtained from interviews with nurses resulted in the creation of 3 themes and 18 codes: “The Impact of Religious Beliefs on Professional and Team Relationships,” “The Impact of Religious Beliefs on Coping with Clinical Challenges,” and “The Impact of Religious Beliefs on a Positive Clinical Environment.” The nurses’ metaphors regarding their religious beliefs and their profession were divided into three different categories based on their common characteristics. Twenty-three different metaphors were created for these categories.
This study highlights, for the first time, how nurses’ religious beliefs shape their perceptions of a positive clinical work environment. The findings demonstrate that these beliefs influence professional relationships, coping strategies, and the overall atmosphere of the workplace. In addition to contributing to the literature, the results have managerial relevance: acknowledging and respecting employees’ individual values can foster motivation, cooperation, and resilience, while also enhancing job satisfaction and the quality of patient care.
Night shift work disrupts sleep and physiological recovery, leading to adverse health outcomes among nurses. While both work and nonwork factors are known to influence sleep and fatigue, few studies have examined their simultaneous and multiple mediating effects on health in night shift nurses.
This study tested a comprehensive model to investigate the relationships among work factors (emotional demands, night shift rotation intervals, and social support), nonwork factors (exercise and work–life interference), sleep disturbance, fatigue, and health in night shift nurses.
A cross-sectional study was conducted with 289 nurses working rotating night shifts at three hospitals in South Korea. Structural equation modeling (SEM) was employed to assess the direct and indirect effects between variables. Data were collected using validated instruments for sleep disturbance, fatigue, emotional demands, social support, exercise, work–life interference, and health.
Work–life interference had the most significant effect on health, both directly and indirectly through sleep disturbance and fatigue. Emotional demands negatively influenced health via sleep disturbance and fatigue. Exercise indirectly improved health by reducing fatigue, but showed no direct effects. Sleep disturbance was a significant predictor of both fatigue and health. Social support did not demonstrate significant direct or indirect effects on health. The final model explained 51.8% of the variance in health outcomes and exhibited strong model fit indices.
Maintaining a work–life balance is critical for improving the health of night shift nurses, as work–life interference directly and indirectly exacerbates health risks through sleep disturbance and fatigue.
These findings highlight the importance of implementing strategies to manage work–life balance, address emotional demands, promote physical activity, and ensure recovery from shift work to support the health of night shift nurses.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：