Palo Alto, Calif.-based Stanford Health Care has adopted an artificial intelligence tool to help inform patients of test results.
Here are six things to know:
1. The AI interprets clinical test and lab results, explaining them in common language, a draft that is then reviewed by physicians before being sent to patients.
2. Stanford built the tool in-house with Amazon Bedrock, a service for developing generative AI applications, using a large language model from AI company Anthropic.
3. The platform is similar to an app that drafts patient portal responses with AI.
4. "It's really about continuing to give back to the patient-provider relationship," said Michael Pfeffer, MD, chief information and digital officer of Stanford Health Care, in a Jan. 10 news release. "We hope this helps make time for that through reduced administrative tasks and by facilitating better communication and faster communication."
5. The health system tested the technology among 10 primary care physicians for a month, incorporating their feedback, then another 24 physicians for two more months.
6. The tool is currently being used by primary care physicians at Stanford, with plans to expand it to specialists later this year. Initial feedback from providers has been positive, the health system said.