Artificial intelligence tools can help physicians predict treatment and survival outcomes in patients with advanced non-small cell lung cancer treated with immunotherapy.

The Family Heart Foundation, a leading research, education and advocacy organization, today announced the publication of a new peer-reviewed study in JACC: Advances demonstrating how its FIND Lp(a)^® Machine Learning Model can identify people with atherosclerotic cardiovascular disease (ASCVD) who are more likely to have high lipoprotein(a) — or Lp(a). The model has already been successfully deployed at five large U.S. healthcare systems participating in the FIND Lp(a) Program that aims to catalyze Lp(a) screening. The model’s high level of precision supports targeted Lp(a) screening as a practical approach for healthcare systems working toward implementation of guideline-recommended universal screening.

New review in Current Topics in Chemistry brings together decades of research on flavonoids isolated from Erythrina plants, a group long valued in traditional medicine and natural product chemistry.

Researchers identified a DPP4 enzyme from Bacteroides vulgatus that inactivates GLP-2, a peptide involved in protecting the intestinal barrier, and worsens colitis in a preclinical model. A natural-product screen identified theaflavin as a BvDPP4 inhibitor that countered this effect, providing a basis for further study of this microbial enzyme-host pathway.