Large language models outperform traditional structured data-based approaches in identifying immunosuppressed patients.

Identifying immunosuppressed patients using structured data can be challenging. Large language models effectively extract structured concepts from unstructured clinical text. Here we show that GPT-4o outperforms traditional approaches in identifying immunosuppressive conditions and medication use by processing hospital admission notes.

[Utility of CT Cardiac Angiography in the Evaluation of Infective Endocarditis and Its Complications].

Infective endocarditis (IE) is an infection that affects the heart valves, endocardium, and great vessels. It has a mortality rate of approximately 30% per year, so early diagnosis is essential to reduce morbidity and mortality. Cardiac angio-CT triggered by electrocardiogram (ECG) has been considered in IE management guidelines in recent years, given its high spatial resolution, contributing to the diagnosis and evaluation of valvular complications (vegetations, perforations, dysfunctions), perivalvular (abscesses, pseudoaneurysms, prosthesis dehiscence, fistulas) and compromised coronary arteries (embolism), allowing early diagnosis and treatment.

The Structure of Bit-String Similarity Networks.

We study the structural properties of networks formed by random sets of bit strings-namely the ordered arrays of binary variables representing, for instance, genetic information or cultural profiles. Two bit strings are connected by a network link when they are sufficiently similar to each other, i.e.

The use of public spatial databases in risk analysis: A US-oriented tutorial.

This tutorial focuses on opportunities and challenges associated with using six large, publicly accessible spatial databases published during the last decade by US federal agencies. These databases provide opportunities for researchers to risk-inform policy by comparing community asset, demographic, economic, and social data, along with anthropogenic and natural hazard data at multiple geographic scales. The opportunities for data analysis come with challenges, including data accuracy, variations in the shape and size of data cells, spatial autocorrelation, and other issues endemic to spatial datasets.