The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Leveraging Generative AI for Privacy-Preserving Synthetic Data Generation in Healthcare
Abstract
Machine learning models require large and diverse data for making accurate inferences. However, large quantities of data are not available in many cases, either due to data privacy issues or rarity of the data. Synthetic data is used to address this requirement as it captures the original distribution and correlation of real datasets. Thereby, guaranteeing high utility by overcoming data scarcity, and privacy challenges. In this chapter, we will discuss the application of generative and foundation models along with privacy-enhancing frameworks that are commonly used to produce realistic and privacy complaint synthetic data. Integrating privacy into synthetic data can dramatically enhance institutional and cross-border cooperation. In addition, the chapter also highlights the necessity of strong evaluation metrics to determine the reliability and domain usefulness of the synthetic data, that provides a scaled avenue of ethical, efficient and privacy-compliant innovation in sensitive healthcare data.
Related Content
|
.
© 2027.
48 pages.
|
|
.
© 2027.
36 pages.
|
|
.
© 2027.
26 pages.
|
|
.
© 2027.
22 pages.
|
|
.
© 2027.
36 pages.
|
|
.
© 2027.
30 pages.
|
|
.
© 2027.
30 pages.
|
|
|