10/14/2025 | Mayo Clinic released by NewsWise

https://www.newswise.com/articles/ensaios-cl-nicos-virtuais-podem-prever-o-sucesso-de-medicamentos-para-insufici-ncia-card-aca 

Mayo Clinic researchers have developed a new way to predict whether existing drugs could be repurposed to treat heart failure, one of the world's most pressing health challenges. By combining advanced computer modeling with real-world patient data, the team has created “virtual clinical trials” that could facilitate the discovery of effective therapies while reducing the time, cost, and risk of unsuccessful studies.

“We have demonstrated that with our framework, we can predict the clinical effect of a drug without the need for a randomized controlled clinical trial. We can say with a high degree of confidence whether a drug is likely to be successful or not,” says Ph.D. Nansu Zong, a biomedical informatics specialist at Mayo Clinic and lead author of the study published in npj Digital Medicine.

An urgent need
Heart failure affects more than 6 million Americans and is the leading cause of hospitalization and death. Despite decades of research, treatment options remain limited, and many clinical trials are unsuccessful. Traditional drug development is expensive and time-consuming, often taking more than a decade and costing about $1 billion to bring a single therapy to market.

Drug repurposing—finding new uses for drugs already approved for other conditions—may offer a faster and less costly path. Because the safety of these drugs is already established, researchers can move directly to studying their potential benefits in new diseases. However, determining which drugs are worth investigating remains a major challenge.

Dr. Zong led the efforts of a multidisciplinary team of experts in biochemistry, molecular pharmacology, cardiovascular medicine, and quantitative health sciences to combine two powerful tools: computational models, which predict how drugs interact with biological systems, and electronic health records (EHRs) from approximately 60,000 patients with heart failure.

Using these tools, the researchers developed virtual clinical trials—also called trial emulations—that mimic the structure of a randomized clinical trial. Instead of recruiting participants, they used existing patient data to create comparison groups and measure outcomes, such as changes in biomarkers that track the progression of heart failure.

To increase the accuracy of these predictions, the team incorporated drug target modeling, a method that uses artificial intelligence to analyze chemical structures in conjunction with biological data, such as protein or gene sequences. This addition helped bridge the gap between real-world patient data and traditional randomized trials.

The team tested this approach with 17 drugs that had already been studied in 226 phase 3 clinical trials for heart failure. Seven had demonstrated benefit, while ten had not. The virtual clinical trials accurately predicted the “direction” of these real-world outcomes.

“This model has the potential to guide large-scale drug development pipelines,” says Dr. Zong. “At the moment, the model can tell us the direction of efficacy—whether a drug will be beneficial—but not yet the level of that effect. That's our next step.”

Faster, smarter clinical research
By identifying which repurposed drugs are most promising, researchers will be able to prioritize them for further clinical testing and focus resources where the likelihood of success is greatest. This could mean faster access to therapies for patients and lower costs for healthcare systems.

Originally developed as an artificial intelligence-based framework for virtual clinical trials, this technology has spawned a broader initiative within Mayo Clinic, led by Ph.D. Cui Tao, Nancy Peretsman and Robert Scully Chair in the Department of Artificial Intelligence and Informatics and vice president of the Mayo Clinic Informatics Platform.  The new effort is exploring three complementary approaches:

• Trial emulation — replicating the design and analysis of a hypothetical or completed trial using real-world data to validate findings or generate evidence
• Trial simulation — creating a simulated trial with real-world data to estimate how an existing treatment would perform in a different population or for a new indication
• Synthetic trials — construction of a trial that replaces or supplements one or more arms with real or modeled patient data

“Clinical trials will always be essential,” says Dr. Tao. "However, this innovation demonstrates how artificial intelligence can make research more efficient, cost-effective, and widely accessible. The integration of trial emulation and simulation, synthetic trials, and biomedical knowledge modeling opens the door to a new paradigm in translational science."

Looking ahead, these innovations may become an integral part of Mayo Clinic's institutional strategy. They could support Mayo's strategic initiatives, such as Precure, by promoting proactive risk prediction and prevention, and Genesis, by bringing information to intelligent care in transplants and personalized interventions.

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education, and research, providing compassion, expertise, and answers to all who seek healing. Visit Mayo Clinic News Network for more information about Mayo Clinic.