Synthetic hematological data
over federated computing frameworks
Our Mission
SYNTHEMA aims to generate reliable, high-quality synthetic data that can shape new virtual patients to further enhance dia-gnostic capacity, assess treatment options and predict outcomes in rare hematological diseases.
The Challenge
Hematological diseases are a large group of disorders resulting from abnormalities in blood cells, lymphoid organs and coagulation factors.
They suffer from a relatively low number of patients and the prevalence of data silos in unconnected clinical sites and registries.
Our work in the rare disease space
We are devoted to expanding the landscape of personalized medicine in rare hematological diseases.
We aim to increase the number of existing samples in the rare hematological disease space.
SYNTHEMA focuses on two highly representative use cases: Sickle Cell Disease (SCD) and Acute Myeloid Leukaemia (AML).
Virtual patients
Novel methods to generate synthetic multimodal
clinical, omics & imaging data
Privacy-by-design
Built-in privacy through the combination of federated
learning (FL), secure multi-party computation (SMPC)
and differential privacy (DP)
Virtual patients
Novel methods to generate synthetic multimodal clinical, omics & imaging data
Privacy-by-design
Built-in privacy through the combination of federated learning (FL), secure multi-party computation (SMPC) and differential privacy (DP)
Ethics and data protection
Ensuring value-sensitive design for
AI development and GDPR compliance
for data collection and processing
Collaboration is key
Embracing open science practices and multidisciplinary
training in rare hematological
Ethics and data protection
Ensuring value-sensitive design for
AI development and GDPR compliance
for data collection and processing
Collaboration is key
Embracing open science practices and multidisciplinary training in rare hematological