Research investigates whether the severity of SARS-CoV-2 infection can be predicted by analyzing the immunophenotype in the blood of cardiovascular disease (CVD) patients.
To get an inside look at the heart, cardiologists often use electrocardiograms (ECGs) to trace its electrical activity and magnetic resonance images (MRIs) to map its structure. Because the two types of data reveal different details about the heart, physicians typically study them separately to diagnose heart conditions.
Now, in a paper published in Nature Communications, scientists in the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard have developed a machine learning approach that can learn patterns from ECGs and MRIs simultaneously, and based on those patterns, predict characteristics of a patient’s heart. Such a tool, with further development, could one day help doctors better detect and diagnose heart conditions from routine tests such as ECGs.
The researchers also showed that they could analyze ECG recordings, which are easy and cheap to acquire, and generate MRI movies of the same heart, which are much more expensive to capture. And their method could even be used to find new genetic markers of heart disease that existing approaches that look at individual data modalities might miss.
Worms can entangle themselves into a single, giant knot, only to quickly unravel themselves from the tightly wound mess within milliseconds. Now, math shows how they do it.
Researchers studied California blackworms (Lumbriculus variegatus) — thin worms that can grow to be 4 inches (10 centimeters) in length — in the lab, watching as the worms intertwined by the thousands. Even though it took the worms minutes to form into a ball-shaped blob akin to a snarled tangle of Christmas lights, they could untangle from the jumble in the blink of an eye when threatened, according to a study published April 28 in the journal Science (opens in new tab).
Explore the latest trends in deep learning and artificial intelligence with five emerging technologies including federated learning, XAI and more!
Using AI to read people’s thoughts? 😀
In a groundbreaking study, scientists employ a ChatGPT-like AI model to passively decode human thoughts with unprecedented accuracy, unlocking new potential in brain imaging and raising privacy concerns.
An artificial intelligence chatbot was able to outperform human doctors in responding to patient questions posted online, according to evaluators in a new study.
Research published in the Journal of the American Medical Association (JAMA) Internal Medicine found that a chatbot’s responses to patient questions, pulled from a social media platform, were rated “significantly higher for both quality and empathy.”
Researchers designed nanoparticles that can deliver mRNA gene editing solutions directly to the lungs to address rare genetic diseases.
A report has found that AI chatbots have created dozens of news websites around the world that focus on “clickbait articles” to generate revenue.
The report published by the news-rating group NewsGuard identified 49 websites across seven different languages that appeared to be generated – or mostly generated – by AI language models. NewsGuard researchers found that these websites tended to use dull language and repeated phrases, which are trademarks of AI chatbots.
While Wilms tumor—also known as nephroblastoma—is rare, it is the most prevalent childhood kidney cancer. Researchers at Children’s Hospital Los Angeles have now pinpointed a disruption in early kidney progenitor cell development that can be linked to the formation of Wilms tumor.
In a study published in Advanced Science, researchers at the GOFARR Laboratory in Urology compared kidney progenitor cells from a tumor with precursor cells from a healthy kidney. Normally, these precursor cells mature into kidney cells, but when their early development is dysregulated, they behave like cancer stem cells.
While most children with Wilms tumor are successfully treated, current therapies are aggressive. A minority of these patients have unfavorable prognoses or relapses; for these children, there is no existing therapy. “By achieving a more precise understanding of how Wilms tumors develop, our goal is to find new treatments for all types of Wilms tumor,” says Laura Perin, Ph.D., Co-Director of the GOFARR laboratory and senior study co-author with Stefano Da Sacco, Ph.D., another researcher at the GOFARR Laboratory.
A new artificial intelligence system called a semantic decoder can translate a person’s brain activity—while listening to a story or silently imagining telling a story—into a continuous stream of text. The system developed by researchers at The University of Texas at Austin might help people who are mentally conscious yet unable to physically speak, such as those debilitated by strokes, to communicate intelligibly again.
The study, published in the journal Nature Neuroscience, was led by Jerry Tang, a doctoral student in computer science, and Alex Huth, an assistant professor of neuroscience and computer science at UT Austin. The work relies in part on a transformer model, similar to the ones that power Open AI’s ChatGPT and Google’s Bard.
Unlike other language decoding systems in development, this system does not require subjects to have surgical implants, making the process noninvasive. Participants also do not need to use only words from a prescribed list. Brain activity is measured using an fMRI scanner after extensive training of the decoder, in which the individual listens to hours of podcasts in the scanner. Later, provided that the participant is open to having their thoughts decoded, their listening to a new story or imagining telling a story allows the machine to generate corresponding text from brain activity alone.
