Healthcare has been slow to adopt synthetic data because it's expensive and hard to mimic actual patient information, The Wall Street Journal reported Aug. 2.
The data is built by applying artificial intelligence algorithms to real-world information, but in healthcare it's been difficult to make it representative of humans, according to the story. It's also unclear just how "synthetic" the data has to be to not subject it to HIPAA violations.
"The complexity and the variability in healthcare and science makes it a really hard problem to solve," Johnson & Johnson CIO Jim Swanson told the newspaper. He said with real patients, so many factors interact, such as the medications they take, whether they smoke and if they need a joint replacement.
"If we're creating a heart-failure algorithm, we really think that those algorithms should be based on actual data and patients that represent the patients that we serve," Peter Fleischut, MD, chief information and transformation officer, told the Journal. When it comes to synthetic data, "I have not yet been convinced that it's truly representative of the patients we serve."