Speaking to the CEO of health tech startup BenevolentAI recently, they revealed how crucial patient data was to their business. With a rise in data from our genome, our wearable devices and various other places, having a secure means of storing and accessing such data is crucial. Indeed, earlier this year the UK's government office for science advocated the use of blockchain for just such a purpose.
A recent paper from researchers at Radboud University suggests an alternative approach however. The technique will be put through its paces in a large-scale study of Parkinson's disease.
Collecting medical data
Data is increasingly important to the medical research process, and a ready supply of it allows researchers to both avoid duplicating work and also to arrive at fresh insights. Bodies such as the European Union have long advocated open data when it comes to medical research, but opening up data in this way has raised concerns amongst patient groups who are concerned about privacy and security of the data being shared.
To tackle this issue, the researchers developed a technique they refer to as Polymorphic Encryption and Pseudonymisation (PEP). PEP allows data to remain secure by pseudonymising and encrypting the data. This means it can't be accessed even by the people that store the data.
What's more, the access to the data is regulated and monitored, thus the team believe it makes it possible to analyze data whilst ensuring that patient privacy is maintained.
It's first outing is a 650 person study into Parkinson's that will see patients monitored over a two year period via wearable devices. The PEP method will allow the data, collected in the Netherlands, to then be shared with researchers around the world.
"In the context of international medical research, personal information is worth its weight in gold. So it's important for the government to invest in an infrastructure that guarantees the protection of this information," the researchers say. "Especially to ensure that people will remain willing to participate in future studies of this sort."
Once the software has been fully tested, the researchers plan to make it available as open source so that others can both use it and build upon it, and they are confident in the utility of PEP.
"The study of Parkinson's should demonstrate the usefulness of PEP. With this showcase as an example, PEP could grow to become the international standard for storing and exchanging privacy-sensitive medical data," the team say.
How it works
Central to the expected success of PEP is the usability of it. Whereas blockchain remains saddled by a lack of really user-friendly interfaces to it, the team hope that no such problems will hinder PEP.
It will allow participants in each study to decide if they would like their data to be used, and managers of the data have no access to it. For researchers, they access the data via a unique key that they're provided with, and the privacy of each participant is assured via a unique pseudonym by which they are referred to each researcher.
It sounds a fascinating approach, and with data so very crucial to medical research it's an approach to follow with interest.
Originally posted at The Horizon Tracker