Digital twins and the rise of complexity data science
Digital twins and the rise of complexity data science
Digital twins (DTs) are no longer confined to engineering. They are reshaping the way we model, simulate, and interact with complex systems, especially in health and life sciences.
At their core, digital twins are dynamic, data-integrated simulations of real-world entities. These models evolve as new data becomes available, enabling continuous learning and predictive insights. Originally applied in aerospace and manufacturing, digital twins have now found fertile ground in biomedicine, urban systems, and climate modeling.
A new frontier in oncology: fighting leukaemia with digital twins
One of the most powerful uses of digital twins today is in healthcare. A standout examples: Acute Myeloid Leukaemia (AML), an aggressive cancer that affects blood and bone marrow.
Treatment outcomes are highly individual, driven by a patient’s molecular and clinical profile.
The AML-DT project, a collaboration across institutions in Finland and the US, is creating personalized digital twins for AML patients.
By combining clinical data, bone marrow samples, and treatment history, the system builds individualized, dynamic models that can simulate disease progression and forecast treatment response.
Doctors and patients can use this interactive tool to explore treatment options, predict outcomes, and make smarter, more personalized decisions. It is safer, faster, and more precise.
The research value of digital twins
Digital twins serve multiple scientific purposes:
They improve continuously. The learning loop means better accuracy and adaptability over time.
They offer transparency. Unlike black-box models, many DT systems use interpretable, mechanistic frameworks.
Toward complexity data science
Beyond specific use cases, digital twins are sparking a broader shift in scientific methodology. They sit at the intersection of simulation, systems thinking, and data-driven learning—core components of Complexity Data Science (CDS).
CDS aims to provide a formal framework for modeling complex, dynamical systems across domains. It is a natural evolution from traditional modeling approaches and holds promise for tackling grand challenges in medicine, climate, and society at large.
Digital twins represent a paradigm shift—not just in how we model reality, but in how we design, test, and deploy solutions. For researchers, they are tools for exploration and engines of interdisciplinary discovery. As we move toward complexity data science, the opportunities for innovation and impact will only grow.
Frank Emmert-Streib et. al, explore the future of complexity data science in their article ‘Moving beyond simulation and learning: Unveiling the potential of complexity data science’, published in PLOS Complex Systems.
Frank Emmert-Streib,
PLOS Complex Systems
Join our complexity science research community
Connect with researchers across disciplines from around the world. Receive curated content and the latest journal updates—delivered straight to your inbox.
Explore further
Biomedicine
The role of complexity science in advancing biomedical research
Explore systems‑level approaches to biomedical research, where complexity science, multi‑scale modeling, and network approaches are helping generate insights into disease progression and health outcomes.
Healthcare
Complex systems and healthcare: a new paradigm
See how complexity science and network‑based modeling are being applied to healthcare, revealing how interconnected factors shape decision‑making and outcomes.
Healthcare
Complex Systems in Healthcare
Browse research applying complex systems approaches to healthcare, including studies in neuroscience, epidemiology, and data‑driven model development.
