Projects

Digital Twin simulations and precision medicine for foster better understanding and management of Parkinson Disease

A Digital Twin Database to Improve Parkinson’s Disease Treatment

Funding: IFAB call for projects

Enabling technology: Advanced Modeling and Simulation, Artificial Intelligence, Big Data Analytics, Digital Twin

Sustainable Development Goals

Precision medicine is increasingly being applied to the treatment of Parkinson’s disease through deep phenotyping, genetics and other omics data. This approach generates large datasets, creating the need for a dedicated database capable of identifying patient subgroups that are more likely to respond to specific treatments. Because original patient data are often difficult to access, the project will use a Digital Twin approach to generate large populations of synthetic “digital patients” that statistically resemble real patients.

The project uses a synthetic Digital Twin database derived from publicly available data, including clinical profiles, biomarkers and genetic information. These data are integrated with new diagnostic tools for Parkinson’s disease, such as gastrointestinal symptoms, gut microbiome analysis and in vitro pathological assessments conducted on iPSC-derived neurons. The additional data will be collected through a small prospective study designed to explore the practical aspects of data collection.

Objectives

The project aims to generate preliminary evidence on how precision medicine can help identify patients who may benefit from specific therapies. The findings are expected to encourage the medical and scientific community to invest in larger databases and prospective studies.

The project also addresses a broader societal need for more efficient and secure data flows. This priority is reflected in initiatives such as the European Commission’s Towards Common Data Spaces programme and recent G7 efforts to establish global standards for data sharing. Traditional anonymisation methods have proven insufficient to meet these objectives, both in terms of protecting privacy and preserving the analytical value of the data.

Initial Challenge

The prevalence of Parkinson’s disease is increasing across Europe. The effective application of a precision medicine model could improve clinicians’ treatment decisions, patient satisfaction and healthcare system efficiency, while potentially generating significant cost savings. However, original patient data are extremely difficult to obtain and are often fragmented across multiple sources, limiting their availability for research and analysis.

Solution

Synthetic data are increasingly regarded as a more effective alternative to traditional anonymisation. The proposed project will be among the first to demonstrate their potential in a complex real-world setting.

Successful implementation will increase awareness and adoption of synthetic data technologies across society. This will improve data mobility while enabling fairer and more transparent data use, including through the identification and reduction of bias.

At present, the time and cost involved in data-driven projects often prevent smaller businesses from competing effectively. The technology developed through this project will help democratise access to data, enabling organisations of different sizes and across multiple sectors to compete on a more equal footing.

Benefits

The project supports a personalised approach to patient treatment by using omics data to create synthetic models, or Digital Twins. This can improve treatment effectiveness while protecting patient privacy. In line with international initiatives promoting secure data sharing, the project addresses the limitations of traditional anonymisation by balancing privacy protection with analytical utility. It also promotes more democratic access to information, helps reduce bias in datasets and supports innovation across different sectors. In the longer term, the project could also influence international policies and standards relating to privacy and data sharing.