Exploring the Utilization of Synthetic Data in Unsupervised Clustering for Opioid Misuse Analysis

Abstract

Privacy and security restrictions on medical data pose challenges to collaborative research, making synthetic data an increasingly attractive solution. Recent advancements in Generative AI technologies, like GAN models, have improved synthetic data generation. This study investigates the use of synthetic data in clustering models for opioid misuse analysis, generating a dataset that replicates real-world data from 2017 to 2019, including demographics and diagnosis codes. By maintaining patient privacy, we enable comprehensive analysis without compromising security. We developed unsupervised clustering models to identify opioid misuse patterns and assessed the effectiveness of synthetic data across four scenarios: training on real dataset and testing on real dataset (TRTR), training on real dataset and testing on synthetic dataset (TRTS), TSTR, and TSTS. Results demonstrate that synthetic data can replicate real data distributions and clustering characteristics as a training set, offering significant potential for collaborative model development and optimization without exposing privacy or security risks.

Figure 1.

Real Data Preparation and Synthetic Data Generation Workflow.

Figure 2.

Percentage of Opioid Misuses and Comorbidities Across Clustering Groups under Different Scenarios in Each Year. Percentage values for scenarios TRTR and TSTR are annotated below and to the right of the markers, corresponding to green and blue lines. Percentage values for scenarios TRTS and TSTS are annotated above and to the left of the markers, corresponding to yellow and red lines.

Figure 3.

Distribution of Patient Demographics Across Clustering Groups under Different Scenarios. Figures (a), (b), and (c) use a common legend.