6295 papers
This study developed and validated a nomogram model using data from 25,391 emergency department patients to effectively predict the risk of prolonged stranded duration, thereby offering a practical tool for managing ED overcrowding.
This study utilizes single-cell RNA sequencing to characterize cellular heterogeneity in a mouse model of Acute Type A Aortic Dissection, identifying specific macrophage subpopulations and signaling pathways involved in the disease while demonstrating that fenofibrate exerts protective effects by modulating macrophage distribution and reducing inflammation.
This study analyzed dietary intake data from 144 participants in the PandrTB pharmacokinetic sub-study to evaluate how food consumption, particularly fat content and nutrient levels in morning meals, may influence the absorption of key anti-tuberculosis drugs used to treat drug-resistant tuberculosis.
This cross-sectional study at a Kenyan national referral hospital demonstrates that acute peritoneal dialysis effectively achieves measurable urea and creatinine clearance in children with acute kidney injury, resulting in a statistically significant reduction in serum solute levels after the first 24 hours of treatment.
This study evaluates four large language models on their ability to generate patient education content for multidrug-resistant organism infections, finding that while Grok-4 achieved the highest scores in accuracy and safety, no model met acceptable standalone standards, necessitating mandatory expert review and human oversight before clinical use.
In a large prostate cancer cohort with limited baseline data, the study found that while conventional Cox models provide a strong and interpretable benchmark, a Hybrid-Cox approach incorporating machine learning offers modest but consistent improvements in long-term discrimination and calibration, whereas Random Survival Forests did not yield consistent gains over standard regression.
This study developed and validated a decision tree-based machine learning model using data from 1,180 Kazakh hypertensive patients in China to effectively predict 3-year major adverse cardiovascular events, identifying LDL-C, age, office systolic blood pressure, and potassium as the top risk factors through SHAP interpretability analysis.
This study introduces a rolling-window framework using MIMIC-IV data that leverages dynamic physiological features at 8-hour intervals to significantly improve the prediction of delirium in mechanically ventilated ICU patients compared to traditional static models.
This Swedish survey study reveals that while most people with multiple sclerosis are satisfied with their medical care, a significant portion independently engages in self-directed health activities—primarily nutrition, supplements, and exercise—driven by a desire to build health reserves and experiment with effective strategies beyond standard recommendations.
This scoping review synthesizes evidence from 14 studies to demonstrate that excessive nursing workload significantly drives turnover intention primarily through burnout and stress, a relationship that can be mitigated by organizational resources like supportive leadership and schedule control rather than financial compensation alone.