Towards an Architecture to Guarantee Both Data Privacy and Utility in the First Phases of Digital Clinical Trials

Abstract

In the era of the Internet of Things (IoT), drug developers can potentially access a wealth of real-world, participant-generated data that enable better insights and streamlined clinical trial processes. Protection of confidential data is of primary interest when it comes to health data, as medical condition influences daily, professional, and social life. Current approaches in digital trials entail that private user data are provisioned to the trial investigator that is considered a trusted party. The aim of this paper is to present the technical requirements and the research challenges to secure the flow and control of personal data and to protect the interests of all the involved parties during the first phases of a clinical trial, namely the characterization of the potential patients and their possible recruitment. The proposed architecture will let the individuals keep their data private during these phases while providing a useful sketch of their data to the investigator. Proof-of-concept implementations are evaluated in terms of performances achieved in real-world environments.

Keywords: IoT; human-centered computing; mobile devices; performance evaluation; privacy protection; security; survey.

Figure 1

A simplified representation of the main phases for conducting digital clinical trials.

Figure 2

A simplified representation of the common approach in which according to Article 32 of GDPR anonymization and/or pseudoanonymization are in charge of the Data Processor and Data Controller.

Figure 3

A simplified reference architecture.

Figure 4

A simplified representation of the privacy-preserving characterization and recruiting phases of clinical trials. Once the user agrees to enroll, data are treated as in the common approach depicted in Figure 2.

Figure 5

Experimental setup.

Figure 6

Time necessary to sign chunks of data of different sizes for an overall of 64,000 bytes. Please note the logarithmic scale.

Figure 7

Execution time (x axis of all four plots, in seconds) of the privacy-preserving clustering algorithm on PC (orange) and gateway (blue), in (A) for a different number of records (y axis, the number of records), in (B) for a different number of gateways (y axis, the number of gateways), in (C) for a different number of features (y axis, the number of features in each record processed by the clustering algorithm), and in (D) for a different number of clusters (y axis, the number of clusters).