# Data Augmentation and Synthetic Data Generation in Rare Disease Research: A Scoping Review

## TL;DR

This review explores how data augmentation and synthetic data help overcome challenges in rare disease research by expanding limited datasets and improving model performance.

## Contribution

The paper provides a comprehensive overview of data augmentation and synthetic data methods applied specifically to rare disease research.

## Key findings

- Imaging data is the most common domain for these methods, followed by clinical and omics datasets.
- Deep generative models have seen rapid growth since 2021, while classical augmentation remains widely used.
- Rule- and model-based methods offer high interpretability for small datasets but are less frequently applied.

## Abstract

Background: Rare diseases represent a significant research challenge due to the limited availability of data, small patient cohorts, and heterogeneous phenotypes. Data augmentation and synthetic data generation are increasingly adopted to mitigate these limitations. Methods: This scoping review maps the application of data augmentation and synthetic data generation methods as strategies to address these limitations. A total of 118 studies published between 2018 and 2025 were identified through PubMed, Scopus, and Electronics Engineers (IEEE) Xplore. Results: Imaging data headed the field, followed by clinical and omics datasets. Classical augmentation, mainly geometric and photometric transformations, emerged as the most frequent approach, while deep generative models have rapidly expanded since 2021. Rule- and model-based methods were less common but demonstrated high interpretability in small datasets. Conclusions: Overall, these techniques enabled dataset expansion and improved model robustness. However, both approaches require rigorous validation to confirm biological plausibility. Together, these methods can transform data scarcity from a barrier into a driver of methodological innovation, enabling more inclusive rare disease research.