Calculating effectiveness of eHealth without sharing any patient information

WOE 16:00 - 16:30

Lezingenzaal 4

The effectiveness of eHealth solutions is hard to prove in a cost-efficient way. Part of this problem is due to data-sharing issues and privacy concerns. What if we could make statistical calculations on separate datasets without revealing or sharing any personal information?

In the Techruption use-case “privacy-preserving analytics” (PPA) we are able to mathematically prove the effectiveness of eHealth solutions through privacy-preserving statistical analysis on private datasets from 3 different organizations: CZ (a health insurance company), Zuyderland (a hospital) and CBS (Statistics Netherlands). With the help of advanced cryptography, secure multi-party computation (MPC), the individual data-items remain encrypted at all times during the analysis; only the final, aggregated result is revealed, and no patient information is shared.

We use a blockchain and a smart contract to control and govern who can do analyses (queries), what datasets can be used, what the minimal anonymity set should be etc. In addition, the blockchain provides an audit trail of all analyses that have been performed.

  • Thema

    Big data zijn onmisbaar, het is de basis voor vrijwel elke beslissing binnen een modern bedrijf. Toch draait het uiteindelijk om het effectief analyseren van alle verzamelde data. Deze analyses tonen nog regelmatig heel verrassende resultaten. Pakt een onderneming de handschoen op om deze resultaten iets minder verrassend te maken, dan ontstaan er enorme businesskansen. Binnen het thema analytics zijn er diverse presentaties die inzicht geven in de mogelijkheden van analytics.