A study by investigators at the Icahn School of Medicine at Mount Sinai, in collaboration with colleagues from Rabin Medical Center in Israel and other collaborators, suggests that even the most advanced artificial intelligence (AI) models can make surprisingly simple mistakes when faced with complex medical ethics scenarios. The findings, which raise important questions about how and when to rely on large language models (LLMs), such as ChatGPT, in health care settings, were reported in the July 22 online issue of NPJ Digital Medicine. 

A study published in Advanced Science introduces a brain-specific "aging clock," developed by researchers in Spain and Luxembourg, that uses gene expression data to measure the biological age of brain cells. This machine learning-based tool, trained on data from healthy individuals aged 20–97, can detect accelerated aging in brain cells of people with neurodegenerative diseases.

The researchers used this clock to screen thousands of compounds, identifying 453 potential interventions—genetic and chemical—that could rejuvenate neural progenitor cells and neurons. Some of these compounds are already known to improve brain function, while most are novel in the context of brain aging.

As proof of concept, three compounds were tested in mice. These reduced anxiety, slightly improved memory, and triggered gene expression changes toward a younger state in the brain, indicating molecular-level rejuvenation.

This study provides a promising new platform for identifying neuroprotective and potentially therapeutic compounds against age-related brain decline, laying the groundwork for future drug development.

Matthew Leming, PhD, and Hyungsoon Im, PhD of the Center for Systems Biology at Massachusetts General Hospital, are the co-corresponding authors of a paper published in Alzheimer’s & Dementia, “Differential dementia detection from multimodal brain images in a real-world dataset.”