Machine Learning News and Research

RSS

Artificial intelligence predicts hospital admissions hours earlier in emergency departments

Artificial intelligence (AI) can help emergency department (ED) teams better anticipate which patients will need hospital admission, hours earlier than is currently possible, according to a multi-hospital study by the Mount Sinai Health System.

11 Aug 2025

Using machine learning framework to identify prognostic biomarkers in neuroblastoma

Neuroblastoma is the most common solid tumor in infants and accounts for nearly 15% of all pediatric cancer-related deaths.

11 Aug 2025

Decoding macrophage immune responses with gene editing and machine learning

Fighting off pathogens is a tour de force that must happen with speed and precision. A team of researchers at CeMM and MedUni Vienna led by Christoph Bock and Matthias Farlik has investigated how macrophages-immune cells that are the body's first responders-master this challenge.

8 Aug 2025

Aging brains lose key proteins despite intact genetic blueprints

An international research team involving the Leibniz Institute on Aging - Fritz Lipmann Institute (FLI) in Jena, the Scuola Normale Superiore Pisa, and Stanford University has discovered that in the aging brain, certain proteins are lost even though their mRNA blueprints remain intact.

8 Aug 2025

How too much screen time affects kids’ heart health and what can reduce the risk

A large Danish cohort study found that higher screen time in childhood and adolescence is linked to worse cardiometabolic health, with shorter sleep amplifying the risk. Blood metabolomics revealed a signature of high screen time, and in teens, it was tied to higher predicted cardiovascular disease risk.

7 Aug 2025

AI-powered sweat sensor predicts anxiety before symptoms appear

Researchers have developed Stressomic, a wearable microfluidic biosensor that sequentially measures cortisol, epinephrine, and norepinephrine in sweat at six-minute intervals. The device distinguishes physical from psychological stress and predicts anxiety levels using machine learning.

7 Aug 2025

Wearable devices could predict cardiovascular disease risk

Wearable health technology tracks more than just your steps these days.

6 Aug 2025

Low oxygen environment protects brain and restores movement in mice with Parkinson's

Researchers from the Broad Institute and Mass General Brigham have shown that a low-oxygen environment - similar to the thin air found at Mount Everest base camp - can protect the brain and restore movement in mice with Parkinson's-like disease.

6 Aug 2025

Excessive screen time linked to higher cardiometabolic risk in youth

Children and young adults who spend excessive hours glued to screens and electronic devices may have higher risks for cardiometabolic diseases, such as high blood pressure, high cholesterol and insulin resistance, according to new research published today in the Journal of the American Heart Association, an open-access, peer-reviewed journal of the American Heart Association.

6 Aug 2025

Lupus Research Alliance awards early career scientists for innovative research

Today, the Lupus Research Alliance (LRA), the world's largest private funder of lupus research, announced the recipients of the 2025 Empowering Lupus Research (ELR) Career Development Award and Postdoctoral Award.

5 Aug 2025

Understanding how long non-coding RNAs control gene expression in cancer

Long non-coding RNAs (lncRNA) are a type of RNA molecule that do not carry instructions to make proteins. Instead, they influence how other genes are expressed.

5 Aug 2025

Advancing healthcare with machine learning and big data at Cedars-Sinai

Two new studies from the Department of Computational Biomedicine at Cedars-Sinai are advancing what we know about using machine learning and big data to improve healthcare and medical research.

4 Aug 2025

AI spots hidden diabetes risk even when test results look normal

Researchers used continuous glucose monitoring and multimodal data from over 3,000 people to reveal hidden patterns in glucose spikes across normoglycemia, prediabetes, and type 2 diabetes. Their AI-driven model exposed high individual variability and offers a personalized path for early detection and prevention of diabetes.

3 Aug 2025