Connect

We expand access to health data and protect privacy with Owkin Connect - our federated learning software.

Our Owkin Connect software provides the infrastructure and AI technology to expand access to healthcare data. It protects patient privacy and complies with data governance rules. Our distributed architecture and federated learning capabilities enable data scientists to securely connect to decentralized multi-party datasets. This helps to train AI models without having to pool data. Data remains local. Only the algorithms travel.

arrow-desktoparrow-mobile

Aggregate models and insights - not data.

Our technology is centered on three core principles: confidentiality, compliance and collaboration. Academic research centers and Biopharma companies deploy Owkin Connect in a wide variety of settings for clinical research, drug discovery and development.

01.

Expand data access to connected partners

02.

Meet global compliance requirements

03.

Build research networks

01.

Expand data access to connected partners

02.

Meet global compliance requirements

03.

Build research networks

FL for biopharma: The MELLODDY project

tip-arrow

The MELLODDY Project is federated learning for drug discovery. Ten pharmaceutical companies collaborate to train machine learning models for drug discovery based on private and highly sensitive screening datasets. Owkin Connect's capabilities help build trust as privacy and security are at the core of the consortium. Our platform is audited yearly by all biopharma partners and external security companies.

Learn more

01.

Sensitive data and assay-specific models remain securely locked on each biopharma’s server.

02.

Lower level model components are securely exchanged and trained over the network with secure aggregation.

03.

Complex but transparent pre-agreed access arrangements are strictly enforced through distributed ledger technology.

2027

According to recent studies, federated learning models can achieve performance levels comparable to ones trained on centrally hosted data sets and, even superior to models that only see isolated single-institutional data. In the second year of the consortium, MELLODDY announced the first demonstration of federated learning improved model performance in drug discovery.

Learn more

FL for clinical research centres: The Healthchain Project

tipArrowDesktop

Federated learning for breast cancer treatment evaluation: The Healthchain Project

Alongside clinical, research, and technology partners, we have established that machine learning models can be trained successfully on histology images, siloed at different clinical centers, to predict treatment responses in breast cancer. The model trained with Owkin Connect can help oncologists choose the most effective breast cancer treatment for each patient based on a single biopsy.

Learn more