Skip to content
Back to news

“Partner of Choice”: Major collaboration in digital twins

What if an AI-based technology existed that could help treat pancreatic cancer? This is the rationale behind our collaboration with Aitia, the leader in the development and application of causal AI and digital twins. Their mission is to discover the next generation of breakthrough drugs in neurodegenerative diseases and oncology. By combining our expertise, our goal is to deliver innovative therapeutic solutions for patients. View the video recap of this partnership.

With Aitia, open innovation serves therapeutic progress

We believe that regular communication and collaboration between diverse stakeholders provide the most effective framework for accelerating innovations that ultimately benefit patients. This principle underpins our multi-year partnership with Aitia, which was established in May of this year. Our primary objective is to utilize causal AI to discover and simulate drugs to fight pancreatic cancer.

00:00 / 00:00

Pancreatic cancer: The 7th most common cause of cancer-related deaths

Pancreatic cancer is one of the cancers with the poorest prognosis, with a 5-year survival rate of just 11%1. Around 500,000 people worldwide are victims of it every year2.

 While diagnosis most often occurs at an advanced stage of the disease, when it is no longer possible to operate on the tumor, the treatment options available to patients are still limited.

Although the causes of pancreatic cancer are still largely unknown, several aggravating factors have been identified. These include smoking and excessive alcohol consumption, as well as diets that are too high in fat and protein, and conditions such as obesity and diabetes.

Pancreatic cancer in figures

  • Pancreatic cancer is the 7th most common cause of cancer-related deaths worldwide3
  • Despite the progress made in terms of diagnosis and treatment, the 5-year survival rate is 11%1
  • In 2020, it was responsible for some 466,000 deaths worldwide3
  • 70.2%: This is the expected increase in the global number of cases by 2040, compared with 2020, on the basis of demographic trends alone4.

Learn more about our commitment on World Pancreatic Cancer Day 2023

Digital Twins: A technology supporting human health

Understanding digital twins

“Digital twins” are computational representations of disease that capture genetic and molecular interactions that causally drive clinical and physiological outcomes. They are based on real-life data drawn from the results of clinical trials.

“The aim with this collaboration is to reduce the risk of attrition – inherent to R&D – and accelerate the discovery of new drugs. We will be able to achieve this by integrating artificial intelligence technologies and digital twins into our R&D processes, enabling us to work with considerably more extensive databases.”

Fabien Schmidlin, Global Head of Translational Medicine at Servier

These “digital replicas” reproduce the mechanical, chemical, electrical and organic processes that occur within the body. Specifically, digital twins make it possible to highlight causal relationships and connections between the different organs.

Adapted for the healthcare sector, digital twins enable us to simulate drug behavior and reveal what works and what does not work for patients. They therefore provide the full representation of a disease based on which each gene can be tested with calculations.

Causal AI in a nutshell

Causal AI is an approach that involves using machine learning algorithms to analyze data and identify existing cause and effect relationships. This methodology is particularly relevant for understanding the treatment response mechanisms at the individual patient level, with the ultimate goal of identifying biomarkers and patient subcategories.

How does this technology benefit patients?

The use of digital twins in health offers real therapeutic benefits for patients.

They make it possible to:

  • Test drug candidates more quickly through ““digital” patient profiles and, ultimately, accelerate the search for, and discovery of, innovative therapeutic solutions.
  • Better understand the connections and causal relationships between the different intracellular signaling pathways, between the different cell types, and the different organs, as well as their reactions to treatments.
  • Assess disease progression and identify subgroups of responder or non-responder patients by identifying biomarkers.
  • Reduce the risk of failure during drug research and development phases.

[1] American Cancer Society. Cancer Facts & Figures 2023. Atlanta: American Cancer Society; 2022.
[2] Pancreatic cancer: A review of epidemiology, trend, and risk factors.
[3] Source: International Agency for Research on Cancer, Globocan 2020, WHO
[4] Source: The Global Cancer Observatory, International Agency for Research on Cancer, 2023