Elvira, Roberto, thank you for joining me today. To start, could you tell us about your academic and professional paths and how you both began collaborating with Math Biology?

Elvira Plenzich: Thank you, Matteo. Roberto and I share a remarkably similar background. I completed both my undergraduate and graduate studies in Mathematics at the University of Salerno. During my master’s program, I had the opportunity to intern with a company, and it was during this period that I first connected with Raffaele Maccioni, thanks to Professor Raffaele Cerulli (Director of the Department of Mathematics, University of Salerno).
Even though it was a virtual interaction due to the pandemic, it opened the door to future collaborations.

That experience eventually led to discussions with my professor Raffaele Cerulli and Raffaele Maccioni, which guided me toward pursuing an Industrial PhD with Math Biology. This was also when I was introduced to Math Biology, whose mission and innovative projects really resonated with my interests in data science and healthcare.

Roberto Tufano: Elvira captured it well. My journey was similar—I also studied Mathematics at the University of Salerno, but my focus during the internship was more programming-oriented, particularly advancing my knowledge in Python. Conversations with Raffaele and learning about Math Biology’s work inspired me to focus on applying mathematical modeling to biological systems. It was an exciting opportunity to combine my passion for healthcare with a practical, research-driven approach.

Math Biology stood out because it bridges advanced technology with a deep commitment to creating impactful solutions in diagnostics. Joining their team has allowed us to explore how decision science can transform healthcare.

Let’s delve into your paper. It addresses challenges related to managing clinical data to support medical decisions. Could you explain how your service-oriented architecture tackles these issues?

Roberto Tufano: Absolutely. One of the biggest challenges clinicians face today is managing the sheer volume of data generated in healthcare settings. These data are often heterogeneous, coming from multiple sources such as medical records, imaging systems, and wearable devices. This can overwhelm clinicians, leading to inefficiencies and potential burnout.

Our architecture integrates artificial intelligence to streamline data processing and provide actionable insights. By adopting a modular service-oriented structure, we allow clinicians to break down large problems into manageable components. Each module is designed to address specific tasks, ensuring the system remains flexible and adaptable to varying needs.

To achieve interoperability, we use the FHIR (Fast Healthcare Interoperability Resources) standard, which ensures seamless data integration across different healthcare systems. This makes it easier for clinicians to access and share patient information efficiently.

Elvira Plenzich: The value of this approach is its ability to reduce repetitive tasks. For instance, when a patient’s medical history is shared between providers, it minimizes the need for manual transcription or redundant tests. This not only improves efficiency but also enhances the overall patient experience. For Math Biology, this approach aligns with our commitment to harnessing technology like DMA to create solutions that are both practical and transformative.

Your work incorporates the “human in the loop” approach. How do you balance human involvement with advanced automation in your system?

Elvira Plenzich: The human-in-the-loop methodology is central to our philosophy. While automation can handle repetitive tasks and generate preliminary analyses, the clinician remains at the core of the decision-making process. For example, AI might suggest diagnostic pathways or treatment plans based on patient data, but it’s the clinician who validates and implements these recommendations.

This approach also allows clinicians to provide feedback that improves the AI over time, ensuring the system evolves alongside their needs.

Roberto Tufano: Absolutely. We want clinicians to view the system as an ally rather than an obstacle. By designing intuitive interfaces that integrate seamlessly with clinical workflows, we aim to minimize disruption while maximizing value. Building trust is another critical factor. Transparency is key, which is why we use explainable AI
models. When clinicians understand how the AI arrives at its recommendations, they’re more likely to trust and adopt the system. This reflects Math Biology’s broader goal of ensuring that technology empowers, rather than replaces, human expertise.

Math Biology’s DMA technology is central to innovation in diagnostics. How do you see it transforming clinical diagnostics?

Roberto Tufano: DMA technology is revolutionary because it’s non-invasive and highly adaptable. In traditional diagnostics, clinicians often rely on invasive procedures or complex imaging techniques, which can be costly, time-consuming, and stressful for patients. DMA provides an alternative that prioritizes early detection while reducing unnecessary interventions.

Elvira Plenzich: Building on Roberto’s point, DMA technology is particularly impactful for conditions where early diagnosis is critical, such as cancer or cardiovascular diseases. By providing detailed metabolic insights, DMA helps clinicians identify risks earlier and tailor treatments more effectively.
At Math Biology, we view this as a step toward precision medicine. While there are challenges in scaling and integrating the technology, the potential benefits for patients and clinicians are enormous.

Looking ahead, what future developments or projects are you considering based on your current research?
Elvira Plenzich: One major project is PREVEDO, a collaboration between Math Biology and the University of Salerno. This initiative involves clinical trials combining DMA technology with traditional diagnostics. It’s a critical step in validating our architecture in real-world settings and demonstrating its effectiveness.

Roberto Tufano: PREVEDO is just the beginning. The modular nature of our system means it could expand beyond medicine into areas like nutrition and sports science. While our immediate focus is on healthcare, the versatility of the architecture opens up opportunities in other fields where data-driven decisions are essential.

At Math Biology, our broader vision is to create tools that are not only innovative but also deeply integrated into everyday practices. We’re excited to see how our work evolves in the coming years.