When Judith Miller had routine blood work done in July, she got a phone alert the same day that her lab results were posted online. So, when her doctor messaged her the next day that her overall tests were fine, Miller wrote back to ask about the elevated carbon dioxide and low anion gap listed in the report.
While the 76-year-old Milwaukee resident waited to hear back, Miller did something patients increasingly do when they can’t reach their health care team. She put her test results into Claude and asked the AI assistant to evaluate the data.
“Claude helped give me a clear understanding of the abnormalities,” Miller said. The generative AI model didn’t report anything alarming, so she wasn’t anxious while waiting to hear back from her doctor, she said.
Patients have unprecedented access to their medical records, often through online patient portals such as MyChart, because federal law requires health organizations to immediately release electronic health information, such as notes on doctor visits and test results. A study published in 2023 found that 96% of patients surveyed want immediate access to their records, even if their provider hasn’t reviewed them.
And many patients are using large language models, or LLMs, like OpenAI’s ChatGPT, Anthropic’s Claude, and Google’s Gemini, to interpret their records. That help comes with some risk, though. Physicians and patient advocates warn tha …