Fine-tuning a local LLaMA-3 large language model for automated privacy-preserving physician letter generation in radiation oncology.

Introduction: Generating physician letters is a time-consuming task in daily clinical practice.

Methods: This study investigates local fine-tuning of large language models (LLMs), specifically LLaMA models, for physician letter generation in a privacy-preserving manner within the field of radiation oncology.

Results: Our findings demonstrate that base LLaMA models, without fine-tuning, are inadequate for effectively generating physician letters.

The association of physical function and physical performance with DNA methylation clocks in oldest-old living in Singapore - the SG90 cohort.

Deoxyribonucleic acid (DNA) methylation (DNAm) clocks estimate biological age according to DNA methylation. This study investigated the associations between measures of physical function and physical performance and ten DNAm clocks in the oldest-old in Singapore. The SG90 cohort included a subset of community-dwelling oldest-old from the Singapore Chinese Health Study (SCHS) and Singapore Longitudinal Ageing Study (SLAS).

A qualitative study on general practitioners' perspectives on late-life depression in Singapore-part II: system- and physician-related factors.

Background: Little is known about the practices and resources employed by general practitioners (GPs) in Singapore to manage late-life depression. As the country is stepping up its efforts to promote collaborative care across community mental health and geriatric care, understanding GPs' current practices when managing late-life depression appears timely.

Methods: This qualitative descriptive study explored the perspectives on late-life depression of 28 private GPs practicing in Singapore through online semi-structured group and individual interviews.

Free-Breathing Respiratory Triggered High-Pitch Lung CT: Insights From Phantom and Patient Scans.

Objective: Respiratory motion can affect image quality and thus affect the diagnostic accuracy of CT images by masking or mimicking relevant lung pathologies. CT examinations are often performed during deep inspiration and breath-hold to achieve optimal image quality. However, this can be challenging for certain patient groups, such as children, the elderly, or sedated patients.