Abstract The Standards for Reporting Diagnostic Accuracy (STARD) 2015 statement
facilitates transparent and complete reporting of diagnostic test accuracy studies. However …

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an
underestimated global problem. In biomedical image analysis, chosen performance metrics …

Validation metrics are key for tracking scientific progress and bridging the current chasm
between artificial intelligence research and its translation into practice. However, increasing …

Screening mammography aims to identify breast cancer at earlier stages of the disease,
when treatment can be more successful. Despite the existence of screening programmes …

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer
death in the United States. Lung cancer screening using low-dose computed tomography …

Automated radiology report generation has the potential to improve patient care and reduce
the workload of radiologists. However, the path toward real-world adoption has been …

Artificial intelligence (AI) has significant potential in healthcare applications, but its training
and deployment faces challenges due to healthcare's diverse data, complex tasks, and the …

Many clinical tasks require an understanding of specialized data, such as medical images
and genomics, which is not typically found in general-purpose large multimodal models …

Although large language models (LLMs) show promise for clinical healthcare applications,
their utility for personalized health monitoring using wearable device data remains …

Predictive artificial intelligence (AI) systems based on deep learning have been shown to
achieve expert-level identification of diseases in multiple medical imaging settings, but can …