Alert button
Picture for Joost van der Linden

Joost van der Linden

Alert button

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

Mar 02, 2023
Josephine Lamp, Mark Derdzinski, Christopher Hannemann, Joost van der Linden, Lu Feng, Tianhao Wang, David Evans

Figure 1 for GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
Figure 2 for GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
Figure 3 for GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
Figure 4 for GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

In this paper we focus on the problem of generating high-quality, private synthetic glucose traces, a task generalizable to many other time series sources. Existing methods for time series data synthesis, such as those using Generative Adversarial Networks (GANs), are not able to capture the innate characteristics of glucose data and, in terms of privacy, either do not include any formal privacy guarantees or, in order to uphold a strong formal privacy guarantee, severely degrade the utility of the synthetic data. Therefore, in this paper we present GlucoSynth, a novel privacy-preserving GAN framework to generate synthetic glucose traces. The core intuition in our approach is to conserve relationships amongst motifs (glucose events) within the traces, in addition to typical temporal dynamics. Moreover, we integrate differential privacy into the framework to provide strong formal privacy guarantees. Finally, we provide a comprehensive evaluation on the real-world utility of the data using 1.2 million glucose traces

Viaarxiv icon