Connect with us
We’re experimenting with AI-generated content to help deliver information faster and more efficiently.
While we try to keep things accurate, this content is part of an ongoing experiment and may not always be reliable.
Please double-check important details — we’re not responsible for how the information is used.

Alzheimer's

Unlocking the Secrets of Heart Health through AI-Powered Mammograms

Mammograms, with the help of artificial intelligence (AI) models, may reveal much more than cancer, according to a new study. The findings highlight how these important cancer screening tools can also be used to assess the amount of calcium buildup in the arteries within breast tissue — an indicator of cardiovascular health.

Avatar photo

Published

on

The American College of Cardiology’s Annual Scientific Session (ACC.25) recently showcased a groundbreaking study that sheds new light on the capabilities of mammograms. These essential cancer screening tools have long been used to detect breast cancer, but now, with the aid of artificial intelligence (AI) models, they can also serve as a window into heart health.

The U.S. Centers for Disease Control and Prevention recommends that middle-aged and older women receive regular mammograms, which are performed over 40 million times annually in the United States. However, radiologists typically do not quantify or report information on breast artery calcifications, which can be seen on these images. This study demonstrates how AI image analysis techniques can automatically analyze breast arterial calcification and provide a cardiovascular risk score.

“We see an opportunity for women to get screened for cancer and also receive a cardiovascular screen from their mammograms,” said Theo Dapamede, MD, PhD, the lead author of the study. The researchers used an AI model to segment calcified vessels in mammogram images and calculate the future risk of cardiovascular events based on data obtained from electronic health record data.

The findings are significant, as heart disease is the leading cause of death in the United States, yet it remains underdiagnosed in women and awareness about this condition lags. By utilizing AI-enabled mammogram screening tools, researchers can identify more women with early signs of cardiovascular disease, taking advantage of routine screenings that many women already receive.

A buildup of calcium in blood vessels is a sign of cardiovascular damage associated with early-stage heart disease or aging. Previous studies have shown that women with calcium buildup in the arteries face a 51% higher risk of heart disease and stroke.

To develop this screening tool, researchers trained a deep-learning AI model on a large dataset, which included images and health records from over 56,000 patients who had a mammogram at Emory Healthcare between 2013 and 2020. The model was then tested for its ability to characterize patients’ cardiovascular risk as low, moderate, or severe based on mammogram images.

The results showed that the AI model performed well in characterizing patients’ cardiovascular risk. After calculating the risk of dying from any cause or suffering an acute heart attack, stroke, or heart failure at two years and five years, the model demonstrated that the rate of these serious cardiovascular events increased with breast arterial calcification level in two of the three age categories assessed – women younger than age 60 and age 60-80, but not in those over age 80.

The researchers also found that women with the highest level of breast arterial calcification (above 40 mm2) had a significantly lower five-year rate of event-free survival compared to those with the lowest level (below 10 mm2). This translates to approximately 2.8 times the risk of death within five years in patients with severe breast arterial calcification compared to those with little to no breast arterial calcification.

The AI model was developed as a collaboration between Emory Healthcare and Mayo Clinic, but it is not currently available for use. If it passes external validation and gains approval from the U.S. Food and Drug Administration, researchers said the tool could be made commercially available for other healthcare systems to incorporate into routine mammogram processing and follow-up care.

The researchers also plan to explore how similar AI models could be used for assessing biomarkers for other conditions, such as peripheral artery disease and kidney disease, that might be extracted from mammograms.

Alzheimer's

Rewinding Stroke Damage and Beyond: The Promise of GAI-17

Stroke kills millions, but Osaka researchers have unveiled GAI-17, a drug that halts toxic GAPDH clumping, slashes brain damage and paralysis in mice—even when given six hours post-stroke—and shows no major side effects, hinting at a single therapy that could also tackle Alzheimer’s and other tough neurological disorders.

Avatar photo

Published

on

The devastating effects of stroke can be irreversible, leading to loss of neurons and even death. However, researchers have made a groundbreaking discovery that may change this grim reality. A team led by Osaka Metropolitan University Associate Professor Hidemitsu Nakajima has developed a revolutionary drug called GAI-17, which inhibits the protein GAPDH involved in cell death.

GAPDH, or glyceraldehyde-3-phosphate dehydrogenase, is a multifunctional protein linked to various debilitating brain and nervous system diseases. The team’s innovative approach was to create an inhibitor that targets this protein, preventing its toxic effects on neurons. When administered to model mice with acute strokes, GAI-17 showed astonishing results: significantly reduced brain cell death and paralysis compared to untreated animals.

The significance of GAI-17 extends far beyond stroke treatment. Experiments revealed no adverse effects on the heart or cerebrovascular system, making it a promising candidate for addressing other intractable neurological diseases, including Alzheimer’s disease. Moreover, the drug demonstrated remarkable efficacy even when administered six hours after a stroke – a critical window that could revolutionize stroke care.

“We believe our GAPDH aggregation inhibitor has the potential to be a single treatment for many debilitating neurological conditions,” Professor Nakajima expressed. “We will continue to explore its effectiveness in various disease models and strive towards creating a healthier, longer-lived society.”

Continue Reading

Alzheimer's

Uncovering the Hidden Culprits Behind Alzheimer’s Disease

A surprising new study has uncovered over 200 misfolded proteins in the brains of aging rats with cognitive decline, beyond the infamous amyloid and tau plaques long blamed for Alzheimer’s. These shape-shifting proteins don’t clump into visible plaques, making them harder to detect but potentially just as harmful. Scientists believe these “stealth” molecules could evade the brain’s cleanup systems and quietly impair memory and brain function. The discovery opens a new frontier in understanding dementia and could lead to entirely new targets for treatment and prevention.

Avatar photo

Published

on

Uncovering the Hidden Culprits Behind Alzheimer’s Disease

For decades, researchers have been trying to understand the root causes of Alzheimer’s disease. While amyloids, such as A-beta and tau proteins, have long been the focus of attention, a new study suggests that these sticky brain plaques may not be the only culprits behind cognitive decline.

Researchers at Johns Hopkins University have made a groundbreaking discovery, identifying over 200 types of misfolded proteins in rats that could contribute to age-related cognitive decline. This finding has significant implications for Alzheimer’s research and opens up new avenues for potential therapeutic targets and treatments.

“We’re seeing hundreds of proteins misfolding in ways that don’t clump together in an amyloid and yet still seem to impact how the brain functions,” said Stephen Fried, an assistant professor of chemistry and protein scientist. “Our research is showing that amyloids are just the tip of the iceberg.”

To reach this conclusion, Fried and his team studied 17 two-year-old rats with varying levels of cognitive impairment. They measured over 2,500 types of protein in the hippocampus, a part of the brain associated with spatial learning and memory. The researchers were able to determine which proteins misfolded for all the rats and are associated with aging in general versus which proteins specifically misfold in cognitively impaired rats.

More than 200 proteins were found to be misfolded in the cognitively impaired rats but maintained their shapes in the cognitively healthy rats. This suggests that some of these misfolded proteins may contribute to cognitive decline, according to the researchers.

Misfolded proteins are unable to carry out tasks necessary for a cell to function properly, so cells have a natural surveillance system that identifies and destroys these misbehaving proteins. However, it appears that some misfolded proteins can escape this surveillance system and still cause problems.

The next step for Fried’s team is to use high-resolution microscopes to get a more detailed picture of what the misfolded proteins look like at the molecular level.

“A lot of us have experienced a loved one or a relative who has become less capable of doing those everyday tasks that require cognitive abilities,” Fried said. “Understanding what’s physically going on in the brain could lead to better treatments and preventive measures.”

This research has significant implications for Alzheimer’s disease, as it suggests that there may be multiple targets for treatment beyond amyloids alone. By understanding the molecular differences between healthy and cognitively impaired brains, researchers can develop more effective treatments and potentially prevent cognitive decline in the first place.

Continue Reading

Alzheimer's

Uncovering the Hidden Defenses Against Alzheimer’s Disease: A Breakthrough Study on Brain Resilience

Scientists at UCSF combined advanced brain-network modeling, genetics, and imaging to reveal how tau protein travels through neural highways and how certain genes either accelerate its toxic journey or shield brain regions from damage. Their extended Network Diffusion Model pinpoints four gene categories that govern vulnerability or resilience, reshaping our view of Alzheimer’s progression and spotlighting fresh therapeutic targets.

Avatar photo

Published

on

Alzheimer’s disease is a complex condition that affects different parts of the brain in various ways. One key factor in the progression of the disease is the misbehavior of tau proteins, which can lead to toxic clumps forming inside neurons and impairing their function. Researchers have long sought to understand why some areas of the brain are more resilient to Alzheimer’s than others, a phenomenon known as selective vulnerability or resilience.

A recent study by researchers at the University of California, San Francisco (UCSF) has made significant strides in this area by combining advanced mathematical modeling with brain imaging and genetics. The study, published in Brain, identified multiple distinct pathways through which risk genes confer vulnerability or resilience to Alzheimer’s disease.

The researchers developed a model called the extended Network Diffusion Model (eNDM), which predicted where tau protein would spread next based on real-world brain connection data from healthy individuals. By applying this model to brain scans of 196 people at various stages of Alzheimer’s, they were able to identify areas that were resistant or vulnerable to the disease.

The study revealed four distinct types of genes: those that boost tau spread along the brain’s wiring (Network-Aligned Vulnerability), those that promote tau buildup in ways unrelated to connectivity (Network-Independent Vulnerability), those that help protect regions that are otherwise tau hotspots (Network-Aligned Resilience), and those that offer protection outside of the network’s usual path (Network-Independent Resilience).

These findings have significant implications for understanding Alzheimer’s disease and developing potential intervention targets. The study’s lead author, Ashish Raj, PhD, noted that their research offers a “hopeful map forward” in understanding and eventually stopping Alzheimer’s disease.

The researchers also highlighted the importance of considering the different biological functions of genes that respond independently of the network versus those that respond in concert with it. This nuanced approach could lead to more effective strategies for identifying potential intervention targets and developing treatments for Alzheimer’s disease.

Continue Reading

Trending