Liu Yintong, Acharya U Rajendra, Tan Jen Hong
NUS-ISS, 25 Heng Mui Keng Terrace, Singapore, 119615, Singapore.
Centre for Health Research, University of Southern Queensland, Springfield, Australia; School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia.
Comput Methods Programs Biomed. 2025 Mar;260:108571. doi: 10.1016/j.cmpb.2024.108571. Epub 2024 Dec 28.
Data sharing in healthcare is vital for advancing research and personalized medicine. However, the process is hindered by privacy, ethical, and legal challenges associated with patient data. Synthetic data generation emerges as a promising solution, replicating statistical properties of real data while enhancing privacy protection.
This systematic review examines deep learning techniques for synthetic data generation in healthcare, focusing on their ability to maintain data utility and enhance privacy. Studies from Scopus, Web of Science, PubMed, and IEEE databases published between 2019 and 2023 were analyzed. Key methods explored include Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models. Evaluation metrics encompass data resemblance, utility, and privacy preservation, with special attention to privacy-enhancing methods like differential privacy and federated learning.
GANs and VAEs demonstrated robust capabilities in generating realistic synthetic data for tabular, signal, image, and multi-modal datasets. Privacy-preserving approaches such as differential privacy and adversarial training significantly reduced re-identification risks while maintaining data fidelity. However, challenges persist in preserving temporal correlations, reducing biases, and aligning with regulatory frameworks, particularly for longitudinal and high-dimensional data.
Synthetic data generation holds significant potential for privacy-preserving data sharing in healthcare. Ongoing research is required to develop advanced algorithms and evaluation frameworks, ensuring synthetic data's quality and privacy. Collaboration between technologists and policymakers is essential to create comprehensive guidelines, fostering secure and effective data sharing in healthcare.
医疗保健中的数据共享对于推进研究和个性化医疗至关重要。然而，这一过程受到与患者数据相关的隐私、伦理和法律挑战的阻碍。合成数据生成作为一种有前景的解决方案出现，它在增强隐私保护的同时复制真实数据的统计特性。
本系统综述研究了医疗保健中用于合成数据生成的深度学习技术，重点关注其保持数据效用和增强隐私的能力。分析了2019年至2023年期间在Scopus、科学网、PubMed和IEEE数据库上发表的研究。探索的关键方法包括生成对抗网络（GAN）、变分自编码器（VAE）和扩散模型。评估指标包括数据相似性、效用和隐私保护，特别关注差分隐私和联邦学习等增强隐私的方法。
GAN和VAE在为表格、信号、图像和多模态数据集生成逼真的合成数据方面表现出强大的能力。差分隐私和对抗训练等隐私保护方法在保持数据保真度的同时显著降低了重新识别风险。然而，在保留时间相关性、减少偏差以及与监管框架保持一致方面仍然存在挑战，特别是对于纵向和高维数据。
合成数据生成在医疗保健中保护隐私的数据共享方面具有巨大潜力。需要持续开展研究以开发先进的算法和评估框架，确保合成数据的质量和隐私。技术专家和政策制定者之间的合作对于创建全面的指导方针至关重要，有助于促进医疗保健中安全有效的数据共享。
