New AI Tool Accelerates Disease Treatments

University of Virginia School of Medicine scientists have created a computational tool to accelerate the development of new disease treatments. The tool goes beyond current artificial intelligence (AI) approaches by identifying not just which patient populations may benefit but also how the drugs work inside cells.

The researchers have demonstrated the tool's potential by identifying a promising candidate to prevent heart failure, a leading cause of death in the United States and around the world.

The new AI tool called LogiRx, can predict how drugs will affect biological processes in the body, helping scientists understand the effects the drugs will have other than their original purpose. For example, the researchers found that the antidepressant escitalopram, sold as Lexapro, may prevent harmful changes in the heart that lead to heart failure, a condition that causes almost half of all cardiovascular deaths in the United States.

"AI needs to move from detecting patterns to generating understanding," said UVA's Jeffrey J. Saucerman. PhD. "Our LogiRx tool helps us identify not just which drugs can be repurposed for heart disease but how they work in the heart."

Heart failure kills more than 400,000 Americans every year. One of its hallmarks is the overgrowth of cells that thicken the heart muscle and prevent the organ from pumping blood as it should. This is known as cardiac hypertrophy.

Saucerman and his team, led by PhD student Taylor Eggertsen, wanted to see if LogiRx could identify drugs with the potential to prevent cardiac hypertrophy and, ultimately, head off heart failure. They used the tool to evaluate 62 drugs that had been previously identified as promising candidates for the task. LogiRx was able to predict "off-target" effects for seven of these drugs that could help prevent harmful cellular hypertrophy, which were confirmed in cells for two of the drugs.

The scientists then evaluated LogiRx’s predictions by doing lab tests and by looking at outcomes in patients taking the drugs. The latter revealed that patients taking escitalopram were significantly less likely to develop cardiac hypertrophy.

"LogiRx identifies unexpected new uses for old drugs that are already shown to be safe in humans," said Eggertsen, in UVA's Department of Biomedical Engineering, a joint program of the School of Medicine and School of Engineering. "This tool can help researchers explore new patient populations that could benefit from a drug or to avoid unwanted side effects."

Additional lab research and clinical trials will be needed before doctors might start prescribing escitalopram for heart health. But Saucerman is excited about the potential of LogiRx for advancing and accelerating new treatments not just for cardiac hypertrophy but for a host of other serious medical conditions.

"AI is accelerating many aspects of drug development, but it has made less progress in providing the required understanding of how these drug work in the body," Saucerman said. "LogiRx is a step towards combining AI with existing knowledge of how cells work to find new uses for old drugs."

Eggertsen TG, Travers JG, Hardy EJ, Wolf MJ, McKinsey TA, Saucerman JJ.
Logic-based machine learning predicts how escitalopram attenuates cardiomyocyte hypertrophy.
Proc Natl Acad Sci U S A. 2025 Mar 11;122(10):e2420499122. doi: 10.1073/pnas.2420499122

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Patients say "Yes..ish" to the…

As artificial intelligence (AI) continues to be integrated in healthcare, a new multinational study involving Aarhus University sheds light on how dental patients really feel about its growing role in...

Brains vs. Bytes: Study Compares Diagnos…

A University of Maine study compared how well artificial intelligence (AI) models and human clinicians handled complex or sensitive medical cases. The study published in the Journal of Health Organization...

'AI Scientist' Suggests Combin…

An 'AI scientist', working in collaboration with human scientists, has found that combinations of cheap and safe drugs - used to treat conditions such as high cholesterol and alcohol dependence...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...