Tune Insight provides a federated health data platform that enables hospitals, research networks, and biopharma companies to collaborate on patient data without moving or centralizing the data. The solution uses privacy‑by‑design encryption and homomorphic techniques to keep data confidential while allowing secure analytics and insights. This approach supports multicenter studies, precision medicine research, and compliance with data protection regulations.
Funding
$3.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
EFounders
Product
Problem
Organizations are increasingly data-driven, but are often unable to fully leverage their data due to data privacy concerns, regulatory restrictions, and the risk of data leaks when collaborating with external parties. Sharing sensitive or confidential data for collective analytics, machine learning, and AI model training is often impossible, limiting the potential for valuable insights and innovation.
Solution
Tune Insight provides an encrypted computing platform that enables secure data collaborations without requiring organizations to transfer or reveal their sensitive data. The platform utilizes federated learning, homomorphic encryption, and other privacy-enhancing technologies (PETs) to perform collective analytics and machine learning on encrypted data. Each participating organization deploys Tune Insight's software close to their data, preparing encrypted partial results that are aggregated by the system. This approach allows authorized users to obtain updated collective insights, such as statistics, forecasts, or machine learning models, without compromising data privacy or control.
Target Audience
The primary target audience includes health centers, networks of health institutions, bio-pharmaceutical companies, and other business sectors that require secure data collaborations to unlock the potential of sensitive data for research, medical innovation, and improved decision-making.
Features
- Federated learning and homomorphic encryption for privacy-preserving data collaboration
- Distributed architecture with software deployed at each participating organization
- Collective analytics and machine learning on encrypted data without data transfer
- GDPR compliance and enhanced data security compared to traditional federated learning
- Scalable architecture supporting collaborations with hundreds of participants
- High performance through parallelizable computations, exceeding the performance of fully homomorphic encryption alone
- Software-based solution that does not require trusted third-party hardware or new infrastructure
- Lattigo open-source multi-party homomorphic encryption library