Our client is a major distributor of pharmaceuticals, a global manufacturer and distributor of medical and laboratory products, and a provider of performance and data solutions for healthcare facilities. To do this effectively, our client relies on the speed and effectiveness of processing large and complex data from around the nation.

Challenges

• Data access and sharing sensitive patient data, can create privacy concerns and impede the sharing and use of this data.
• Data integration from multiple sources and in different formats can be difficult and time-consuming.
• Scalability as the data grows, the team would have to ensure that their privacy-preserving ecosystem is able to scale to handle large amounts of data.

 

Solution

The team began by identifying the types of data that would be necessary for drug discovery research, including patient medical records, genetic data, and clinical trial data. They then assessed the privacy risks associated with each type of data and determined the appropriate privacy-preserving techniques to use.

 

To protect patient medical records, the team implemented a secure data sharing platform that uses secure multiparty computation (SMC) to enable the sharing of data without revealing the underlying sensitive information. SMC allows multiple parties to jointly compute a function on their private inputs without revealing anything but the output. This allows researchers to access the necessary data without compromising patient privacy. For genetic data, the team used differential privacy, a technique that adds noise to the data to protect against re-identification while still preserving the usefulness of the data for research. Finally, for clinical trial data, the team used homomorphic encryption, a technique that enables computations to be performed on encrypted data without the need to decrypt it first. This allows researchers to analyze the data without compromising patient privacy.