Author summary Digital technologies are expected to revolutionize healthcare, yet digital healthcare has not reached its full potential. A major bottleneck is the poor data availability. Due to concerns regarding privacy and cost, healthcare data is very difficult to access. Here, our aim was to provide a general-purpose statistical model that can be used in place of actual data. Recent advancements in machine-learning technology, especially in generative models, make this challenging goal possible. We built a model that captures complex statistical interactions among more than 2000 human attributes and made it available as a software service on the Internet. The model can be used for estimating unknown attributes from known attributes and generating synthetic data. We believe that this model significantly lowers the barrier to entry into digital healthcare and will stimulate future innovations.
Figures
Abstract
Data for healthcare applications are typically customized for specific purposes but are often difficult to access due to high costs and privacy concerns. Rather than prepare separate datasets for individual applications, we propose a… [62159 chars]
Source: PLOS (Public Library of Science) | Published: 2025-11-05T00:00:00Z
Credit: PLOS (Public Library of Science)
