Utilization of Generative AI-drafted Responses for Managing Patient-Provider Communication
The integration of generative AI (GenAI) in patient communication presents benefits and challenges. This retrospective observational study analyzed EHR audit logs to assess how 75 healthcare professionals (HCPs) utilized AI-generated drafts for patient messages from October 2023 to August 2024 at a large health system in New York City. Overall utilization was low (19.4%), though prompt refinements improved usage (from 12% to 20%), particularly among physicians. GenAI drafts were generated for all messages, including 80% that received no response, adding to the review burden and potentially undermining efficiency. Text analysis showed HCPs preferred concise, information-rich drafts, with role-based differences-physicians favored shorter drafts, while clinical support staff preferred more empathetic responses. AI-generated drafts reduced message turnaround time by 6.76% despite a marginal increase in required steps (InBasket actions). These findings highlight the need for targeted GenAI deployment strategies, better aligned with clinician workflows and optimized draft generation for improved efficiency.
Authors
- Antoinette Schoenthaler (ORCID: https://orcid.org/0000-0003-4905-5136)
- Oded Nov (ORCID: https://orcid.org/0000-0001-6410-2995)
- David Mann (ORCID: https://orcid.org/0000-0002-2099-0852)
- Adam Szerencsy (ORCID: https://orcid.org/0000-0002-0066-4400)
- Safiya Richardson (ORCID: https://orcid.org/0000-0002-8576-1102)
- Batia M. Wiesenfeld (ORCID: https://orcid.org/0000-0002-6854-1976)
- Vincent J. Major (ORCID: https://orcid.org/0000-0003-2604-3458)
- Soumik Mandal (ORCID: https://orcid.org/0000-0003-3602-703X)
- William Small (ORCID: https://orcid.org/0009-0007-3105-6495)
Institutions
- NYU Langone Health (US)
- New York University (US)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-10-02
- DOI
- https://doi.org/10.1038/s41746-025-01972-w
- Citations
- 5
- Primary Topic
- Electronic Health Records Systems
- Type
- article
- Field-Weighted Citation Impact
- 14.69
Funders
- National Science Foundation