"Reading the invisible": POSTECH-led team develops AI framework accounting for hidden defects in metal 3D printing
Peer-Reviewed Publication
This month, we’re focusing on artificial intelligence (AI), a topic that continues to capture attention everywhere. Here, you’ll find the latest research news, insights, and discoveries shaping how AI is being developed and used across the world.
Updates every hour. Last Updated: 3-Nov-2026 16:16 ET (3-Nov-2026 21:16 GMT/UTC)
POSTECH-Led Team Develops AI Framework Accounting for Hidden Defects in Metal 3D Printing.
Researchers have identified the best dosage for each ADHD medication using data from thousands of people with the condition.
Meta-analysis of 37 studies totalling more than half a million pregnancies with antidepressant use found no significant link between common antidepressant use during pregnancy and autism/ADHD in children after adjusting for the mother’s mental health and other factors.
Before accounting for confounding factors, the study found a small association between antidepressant use during pregnancy and autism or ADHD in children. However, this link was also seen with antidepressant use in mothers before conception and in fathers during pregnancy, suggesting the association reflects parental mental health and genetics rather than the medication itself.
Authors say doctors and patients should weigh the benefit and risks of antidepressant use for moderate to severe depression in pregnancy with the potential harms of a depression relapse. They highlight that supporting good mental health for both mothers and fathers is beneficial for a child’s neurodevelopment.
Current evidence does not support a causal link between the use of almost all antidepressants during pregnancy and an increased risk of neurodevelopmental disorders, including autism and attention-deficit/hyperactivity disorder (ADHD), in children, according to a systematic review and meta-analysis published in The Lancet Psychiatry journal.Childhood epilepsy lacks reliable non-invasive biomarkers for precise diagnosis. A new study in Engineering reveals that N-glycans on serum extracellular vesicles act as a promising liquid-biopsy signature. Researchers optimized extracellular vesicle isolation and used mass spectrometry combined with machine learning to identify 47 key glycans that clearly distinguish healthy children from those with focal or generalized epilepsy, offering a new path for better clinical detection and monitoring.
UC San Diego researchers find that a simple technology that measures blood volume changes coupled with machine learning can be used to screen for peripheral artery disease with a high degree of accuracy.