Approaching Universal Prenatal Detection of Significant Cardiovascular Malformations in Nevada.

Objective: To report our recent experience with prenatal detection of significant cardiovascular malformations (CVMs) in Nevada's state-wide maternal population receiving prenatal care.

Methods: We queried our databases for those with significant CVMs diagnosed pre- or postnatally between May 1, 2021, and April 30, 2024. We defined CVMs as those that required, would have required, or will likely require a therapeutic procedure in the first 12 months.

ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics.

Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals. We develop ReXamine-Global, a LLM-powered, multi-site framework that tests metrics across different writing styles and patient populations, exposing gaps in their generalization. First, our method tests whether a metric is undesirably sensitive to reporting style, providing different scores depending on whether AI-generated reports are stylistically similar to ground-truth reports or not.

Infectious disease outbreaks in the wake of natural flood disasters: global patterns and local implications.

Climate change is an urgent global health challenge, with floods becoming increasingly frequent and exacerbating the spread of infectious diseases. With its diverse climates and recurring natural disasters, Latin America is particularly susceptible to outbreaks following floods. These events disrupt ecosystems and create ideal conditions for the spread of waterborne and vector-borne pathogens.