Peer-Reviewed Publication
NEJM Catal Innov Care Deliv2026;7(7):CAT250377.July 1, 2026Journal Article
Blueprint for Safety: Implementing a Clinically Governed AI Digital Assistant for Patient Guidance.
Claire O'Connell Boogaard1,2, Jaclyn Marshall3, Ankoor Shah4,5, Omid Razmpour6,7, Hasier Pastor Larrieta8, Ami Parekh9
1Patient Safety Officer, Included Health, San Francisco, CA, USA.
2Adjunct Associate Professor, The George Washington University School of Medicine and Health Sciences, Washington, DC, USA.
3Senior Health Economics and Outcomes Research Director, Included Health, San Francisco, CA, USA.
4Vice President, Clinical Excellence, Included Health, San Francisco, CA, USA.
5Adjunct Assistant Professor, Department of Pediatrics, Morehouse School of Medicine, Atlanta, GA, USA.
6Visiting Ph.D. Student, Sloan School of Management, Massacusetts Institute of Technology, Cambridge, MA, USA.
7Former Nurse and Ph.D/M.B.A. Candidate, Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA, USA.
8Senior Software Engineer, Included Health, San Francisco, CA, USA.
9Chief Health Officer, Included Health, San Francisco, CA, USA.
Abstract
Patients navigating a fragmented health care system may feel increasingly tempted to turn to publicly available large language models for quick answers to clinical questions; however, these tools were not built with patient safety, risk stratification, or escalation pathways in mind. In this case study, the authors describe how Included Health designed, piloted, and clinically governed a risk-stra…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans