Readability of Online Patient Educational Materials for Rosacea: Systematic Web Search and Analysis.

Most online educational materials about rosacea exceed recommended readability levels, often requiring at least a high school education to understand, with content authored by physicians being significantly more difficult to read than that written by nonphysicians.

Family History as a Dominant Risk Factor for Uninvestigated Dyspepsia and Chronic Constipation: A Rome IV-Based Study among Japanese University Students.

Background Uninvestigated dyspepsia (UD) and chronic constipation (CC) are common disorders of gut-brain interaction (DGBI). However, limited research has assessed their risk factors in young adults, particularly the influence of family history. This study investigated the associated factors for UD and CC, focusing on family history among Japanese university students.

Endoscopic Retrograde Cholangiopancreatography (ERCP)-Related Duodenal Perforation: Management Challenges and Lessons From a Case Series.

Duodenal perforation is a rare but harmful complication of endoscopic retrograde cholangiopancreatography (ERCP). Early diagnosis and appropriate management are critical to reduce morbidity and mortality. Four patients, aged 36 to 56 years, underwent ERCP for biliary obstruction due to choledocholithiasis or postoperative biliary stricture.

Explainable Machine Learning Assists in Revealing Associations Between Polysomnographic Biomarkers and Incident Type 2 Diabetes in Men.

Introduction: Type 2 diabetes (T2D) shows bidirectional relationships with polysomnographic measures. However, no studies have searched systematically for novel polysomnographic biomarkers of T2D. We therefore investigated if state-of-the-art explainable machine learning (ML) models could identify new polysomnographic biomarkers predictive of incident T2D.

Adaptive radiotherapy dose prediction on head and neck cancer patients with a 3D multi-headed U-Net deep learning architecture.

Online adaptive radiation therapy (ART) personalizes treatment plans by accounting for daily anatomical changes, requiring workflows distinct from conventional radiotherapy. Deep learning-based dose prediction models can enhance treatment planning efficiency by rapidly generating accuracy dose distributions, reducing manual trial-and-error and accelerating the overall workflow; however, most existing approaches overlook critical pre-treatment plan information-specifically, physician-defined clinical objectives tailored to individual patients. To address this limitation, we introduce the multi-headed U-Net (MHU-Net), a novel architecture that explicitly incorporates physician intent from pre-treatment plans to improve dose prediction accuracy in adaptive head and neck cancer treatments.