Revolutionizing cardiovascular risk assessment with AI

International consortium of researchers tests scanning retina with AI

2024-10-04

(Press-News.org) A recent position paper in the Asia-Pacific Journal of Ophthalmology explores the transformative potential of artificial intelligence (AI) in ophthalmology. Led by Lama Al-Aswad, Professor of Ophthalmology and Irene Heinz Given and John La Porte Given Research Professor of Ophthalmology II, of the Scheie Eye Institute, the work represents a collaboration among researchers from Penn Engineering, Penn Medicine, the University of Michigan Kellogg Eye Center, St. John Eye Hospital in Jerusalem, and Gyeongsang National University College of Medicine in Korea.

With fundus photography enabling the visualization of retina at the back of the eye, the potential of AI in providing systemic disease biomarkers is becoming a reality. When fundus images are of sufficient quantity and quality, it becomes possible to train AI systems to detect elevated HbA1c levels — an important marker for high blood sugar that is traditionally obtained with blood draws, which indicates a heightened risk of diabetes and cardiovascular disease. This process leverages the emerging field of oculomics, which studies ophthalmic biomarkers to gain insights into systemic health.

In their manuscript, titled “Development of Oculomics Artificial Intelligence for Cardiovascular Risk Factors: A Case Study in Fundus Oculomics for HbA1c Assessment and Clinically Relevant Considerations for Clinicians,” this multi-institutional team explores the potential of oculomics and highlights pertinent topics for clinicians to consider as we move into an era where artificial intelligence has the potential to enhance systemic health through eye care.

Their discussion is supported by preliminary research results from a pilot study that trained AI models to predict HbA1c levels based on fundus images. This study evaluated various factors — such as AI model size and architecture, the presence of diabetes, and patient demographics (age and sex) — and their impact on AI performance.

One of the study observations was that biased training samples for an oculomics model, such as a pool of predominantly older patients, can degrade model performance. The results of the case study highlight the importance of developing trustworthy AI models for assessing cardiovascular risk factors while addressing the challenges and problems that must be overcome prior to clinical adoption, as well as advancing reliable oculomics technology.

"By leveraging AI to analyze retinal images for cardiovascular risk assessment,” says Al-Aswad, “we aim to bridge a crucial gap in early disease detection. This method not only enhances our ability to identify at-risk individuals but also holds promise for transforming how we manage chronic conditions such as diabetes. By focusing on practical applications of this technology, we are advancing towards more personalized and preventative healthcare solutions.”

“While these advancements hold promise, it is also of utmost importance for clinicians and researchers to develop and employ these techniques in a responsible manner, as this will benefit patient care the most in the end,” adds Kuk Jin Jang, a postdoctoral researcher in the Penn Research in Embedded Computing and Integrated Systems Engineering (PRECISE) Center at the University of Pennsylvania.

“Our collaboration serves to further understand how we can responsibly leverage this revolutionary technology to benefit patients in the future. It is a testament to the collaborative advances formed when healthcare and engineering come together to work towards responsible AI for patient care,” says Joshua Ong, a resident physician at the University of Michigan and PRECISE Center affiliate. “I am incredibly grateful for our multidisciplinary team for coming together to bring this paper and topic to the forefront.”

“This collaboration reflects a deep commitment to advancing healthcare through innovative AI applications,” adds PRECISE Center Director Insup Lee, Cecilia Fitler Moore Professor in Computer and Information Science at Penn Engineering. “By combining our expertise, we are paving the way for significant improvements in patient care and the overall management of long-term health challenges.”

END

ELSE PRESS RELEASES FROM THIS DATE:

Antarctic ‘greening’ at dramatic rate

2024-10-04

Vegetation cover across the Antarctic Peninsula has increased more than tenfold over the last four decades, new research shows. The Antarctic Peninsula, like many polar regions, is warming faster than the global average, with extreme heat events in Antarctica becoming more common. The new study – by the universities of Exeter and Hertfordshire, and the British Antarctic Survey – used satellite data to assess how much the Antarctic Peninsula has been “greening” in response to climate change. It found that the area of vegetation ...

Winds of change: James Webb Space Telescope reveals elusive details in young star systems

2024-10-04

Every second, more than 3,000 stars are born in the visible universe. Many are surrounded by what astronomers call a protoplanetary disk – a swirling "pancake" of hot gas and dust from which planets form. The exact processes that give rise to stars and planetary systems, however, are still poorly understood. A team of astronomers led by University of Arizona researchers has used NASA's James Webb Space Telescope to obtain some of the most detailed insights into the forces that shape protoplanetary disks. The observations offer glimpses into what our solar system may have looked like 4.6 billion years ago. Specifically, the team was able to trace so-called ...

UC Merced co-leads initiative to combat promotion and tenure bias against Black and Hispanic faculty

2024-10-04

Black and Hispanic faculty members seeking promotion at research universities face career-damaging biases, with their scholarly production judged more harshly than that of their peers, according to a groundbreaking initiative co-led by the University of California, Merced that aims to uncover the roots of these biases and develop strategies for change. Junior professors are generally evaluated and voted on for promotion and tenure by committees comprising senior colleagues. In one of the studies conducted by the research team, results suggest that faculty from underrepresented minorities received 7% more negative votes from ...

Addressing climate change and inequality: A win-win policy solution

2024-10-04

Climate change and economic inequality are deeply interconnected, with the potential to exacerbate each other if left unchecked. A new study published in Nature Climate Change sheds light on this critical relationship using data from eight large-scale Integrated Assessment Models (IAMs) to examine the distributional impacts of climate policies and climate risks. The study provides robust evidence that climate policies aligned with the Paris Agreement can mitigate long-term inequality while addressing climate change. Led by Johannes Emmerling, Senior Scientist at the Euro-Mediterranean ...

Innovative catalyst produces methane using electricity

2024-10-04

Researchers at the University of Bonn and University of Montreal have developed a new type of catalyst and used it in their study to produce methane out of carbon dioxide and water in a highly efficient way using electricity. Methane can be used, for example, to heat apartments or as a starting material in the chemical industry. It is also the main component of natural gas. If it is produced using green electricity, however, it is largely climate neutral. The insights gained from the model system studied by the researchers can be transferred to large-scale technical ...

Liver X receptor beta: a new frontier in treating depression and anxiety

2024-10-04

Houston, Texas – In a state-of-the-art Bench to Bedside review published in the journal Brain Medicine (Genomic Press), researchers Dr. Xiaoyu Song and Professor Jan-Åke Gustafsson from the University of Houston and Karolinska Institutet (Sweden) shed light on the therapeutic potential of liver X receptor beta (LXRβ) in treating depression and anxiety. This comprehensive analysis marks a significant step forward in understanding the molecular underpinnings of mental health disorders and potentially revolutionizing their treatment. LXRβ, a nuclear receptor initially known for its role in cholesterol metabolism and inflammation, is now emerging as a crucial ...

Improving fumaric acid production efficiency through a ‘more haste, less speed’ strategy

2024-10-04

As plastic waste continues to build up faster than it can decompose, the need for biodegradable solutions is evident. Previously, Professor Yutaka Amao and his team at Osaka Metropolitan University’s Research Center for Artificial Photosynthesis succeeded in synthesizing fumaric acid, a raw material for biodegradable plastics from biomass-derived pyruvic acid and carbon dioxide. However, the fumaric acid production process reported earlier has a problem with producing undesirable substances as byproducts in addition to L-malic acid, which is ...

How future heatwaves at sea could devastate UK marine ecosystems and fisheries

2024-10-04

The oceans are warming at an alarming rate. 2023 shattered records across the world’s oceans, and was the first time that ocean temperatures exceeded 1oC over pre-industrial levels. This led to the emergence of a series of marine heatwave events across both hemispheres, from the waters around Japan, around South America, and across the wider North Atlantic. Marine heatwaves are periods of extremely warm sea temperatures that can form in quite localized hot spots but also span large parts of ocean ...

Glimmers of antimatter to explain the "dark" part of the universe

2024-10-04

One of the great challenges of modern cosmology is to reveal the nature of dark matter. We know it exists (it constitutes over 85% of the matter in the Universe), but we have never seen it directly and still do not know what it is. A new study published in JCAP has examined traces of antimatter in the cosmos that could reveal a new class of never-before-observed particles, called WIMP (Weakly Interacting Massive Particles), which could make up dark matter. The study suggests that some recent observations ...

Kids miss out on learning to swim during pandemic, widening racial and ethnic disparities

2024-10-04

Nearly three out of four kids in Chicago had no swimming lessons in summer of 2022, with significant racial and ethnic differences, according to a parent survey from Ann & Robert H. Lurie Children’s Hospital of Chicago published in Pediatrics. Black and Hispanic/Latine kids were disproportionately affected (85 percent and 82 percent, respectively), compared to white kids (64 percent). The most common reasons for not getting swimming lessons also differed among racial and ethnic groups. Parents of White kids reported they ...

Revolutionizing cardiovascular risk assessment with AI

ELSE PRESS RELEASES FROM THIS DATE:

LAST 30 PRESS RELEASES: