The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review.

The adoption of machine learning (ML) and, more specifically, deep learning (DL) applications into all major areas of our lives is underway. The development of trustworthy AI is especially important in medicine due to the large implications for patients' lives. While trustworthiness concerns various aspects including ethical, transparency and safety requirements, we focus on the importance of data quality (training/test) in DL.

SLAM-Drop-seq reveals mRNA kinetic rates throughout the cell cycle.

RNA abundance is tightly regulated in eukaryotic cells by modulating the kinetic rates of RNA production, processing, and degradation. To date, little is known about time‐dependent kinetic rates during dynamic processes. Here, we present SLAM‐Drop‐seq, a method that combines RNA metabolic labeling and alkylation of modified nucleotides in methanol‐fixed cells with droplet‐based sequencing to detect newly synthesized and preexisting mRNAs in single cells.

Morphological Macular Changes Under Brolucizumab Treatment for Neovascular Age-Related Macular Degeneration Refractory to Previous Anti-VEGF Treatment Compared with Treatment-Naive Eyes.

Purpose: To evaluate the morphological macular changes and fluid dynamics under brolucizumab treatment in eyes refractory to previous anti-vascular endothelial growth factor (anti-VEGF) treatment for neovascular age-related macular degeneration (nAMD) compared with treatment-naive eyes.

Methods: Retrospective study of all eyes treated with brolucizumab for nAMD between 2020 and 2021 with a fixed injection regimen and one year follow-up. Treatment-naive eyes (TN) were compared with eyes refractory to previous treatment with bevacizumab, ranibizumab, or aflibercept (RT).