Liver Injury due to Intravenous Methylprednisolone in the Drug-Induced Liver Injury Network.

Background And Aims: Short courses of intravenous (iv) methylprednisolone (MP) can cause drug induced liver injury (DILI). The aim of this study was to assess the clinical features and HLA associations of MP-related DILI enrolled in the US DILI Network (DILIN).

Methods: DILIN cases with MP as a suspected drug were reviewed.

Uncertainty-aware diabetic retinopathy detection using deep learning enhanced by Bayesian approaches.

Deep learning-based medical image analysis has shown strong potential in disease categorization, segmentation, detection, and even prediction. However, in high-stakes and complex domains like healthcare, the opaque nature of these models makes it challenging to trust predictions, particularly in uncertain cases. This sort of uncertainty can be crucial in medical image analysis; diabetic retinopathy is an example where even slight errors without an indication of confidence can have adverse impacts.

Comparative Outcomes of Warfarin vs. Direct Oral Anticoagulants (DOACs) in Anticoagulant-Related Gastrointestinal Bleeding: A Single-Center Study.

Background: The management of thromboembolic risk and the necessity for timely hemorrhage control make anticoagulant-related gastrointestinal (GI) bleeding clinically challenging.

Objective: This study aimed to evaluate clinical outcomes (such as bleeding control and mortality) and the effectiveness of anticoagulation reversal techniques in patients with anticoagulant-related GI bleeding in emergency settings.

Methodology: This prospective, observational study conducted at Lady Reading Hospital, Peshawar, from January to December 2023, included patients aged 18 or older with GI bleeding on warfarin or direct oral anticoagulants (DOACs).

Predicting sinonasal inverted papilloma attachment using machine learning: Current lessons and future directions.

Background: Hyperostosis is a common radiographic feature of inverted papilloma (IP) tumor origin on computed tomography (CT). Herein, we developed a machine learning (ML) model capable of analyzing CT images and identifying IP attachment sites.

Methods: A retrospective review of patients treated for IP at our institution was performed.

Long-term outcomes of pediatric temporal bone fractures with hearing loss: Results of a multinational database analysis.

Introduction: Pediatric temporal bone fractures (TBFs) can result in adverse outcomes including meningitis, significant sensorineural hearing loss requiring cochlear implantation (CI), facial nerve weakness, cerebrospinal fluid (CSF) leak, and labyrinthitis. The objective of this study is to determine the risks of these outcomes for TBFs with hearing loss.

Methods: Using the multinational TriNetX database, a retrospective cohort study was performed of patients less than 18 years old with diagnostic codes for other fracture of base of skull and hearing loss to serve as an approximation of TBF.