dAIbetes

Federated virtual twins for privacy-preserving personalised outcome prediction of type 2 diabetes treatment

Project leaders: Alexandros Tanzanakis, Björn Eskofier

Project members: Alexandros Tanzanakis, Mahdis Habibpourfatideh

Start date: 01.01.2024

End date: 31.12.2028

Short description

In dAIbetes, we employ federated learning to develop a global health data platform that enables the creation of internationally trained virtual twin models for type 2 diabetes. Our models draw on large datasets from diverse sources while maintaining strict privacy standards. This groundbreaking method aims to enhance treatment outcome predictions, an area currently without precise guidelines, by using data from approximately 800,000 patients worldwide.
Our objective is to improve prediction accuracy by at least 10% compared to standard models, advancing personalized care for diabetes and other complex diseases. Our team combines expertise in AI, software development, privacy, and diabetes treatment, focusing on the essential balance between safeguarding data privacy and meeting medical research needs.

More information can be found here.

Abstract

Virtual twins have the potential to be used as prognostic tools in precision medicine to support individualized disease management. However, training these models requires large volumes of data from various sources, which is challenging due to privacy regulations like the General Data Protection Regulation (GDPR). Recently, privacy-preserving computational methods, such as federated learning, have emerged, offering a way to utilize extensive data effectively while protecting sensitive patient information.
In dAIbetes, our main medical objective is to provide personalized predictions of treatment outcomes for type 2 diabetes, a condition affecting 1 in 10 adults globally and leading to annual costs of approximately 893 billion EUR. Although healthcare professionals are improving at addressing diabetes risk factors like diet and exercise, there are currently no guidelines for predicting treatment outcomes tailored to individual patients.
dAIbetes brings together advaned expertise in federated learning, artificial intelligence, cybersecurity, diabetes data standardization, clinical validation, as well as in legal and ethical evaluation of applying advanced federated machine learning to personalized medicine. 13 Partners from 13 European countries and the US will jointly implement the project which is structured into 9 Work Packages (WP1-WP9). At FAU, we are working on WP3, i.e., the development of virtual twin apps for training of virtual twin models that will use data from type 2 diabetes patients.