Article Text

Download PDFPDF
Ghost in the inbox: AI may help alleviate the burden of patient messages
  1. Christian Rose,
  2. Carl Preiksaitis
  1. Department of Emergency Medicine, Stanford University School of Medicine, Stanford, California, USA
  1. Correspondence to Dr Christian Rose, Emergency Medicine, Stanford University, Stanford, California, USA; ccrose{at}

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Commentary on: Ayers JW, Poliak A, Dredze M, Leas EC, Zhu Z, Kelley JB, Faix DJ, Goodman AM, Longhurst CA, Hogarth M, Smith DM. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med. 2023 Jun 1;183(6):589-596. doi: 10.1001/jamainternmed.2023.1838.


Implications for practice and research

  • AI assistants could be used to draft responses for physicians and nurses, potentially addressing a key element of burn-out.

  • Further research is needed to assess the impact of communication on healthcare outcomes and should incorporate patient evaluations and feedback.


In the setting of increasing adoption of virtual healthcare and the surge in electronic patient messages, there has been a higher workload for physicians and nurses, contributing to burnout and potentially terse, unanswered or unhelpful patient messages. Given these challenges, there is a need to explore innovative solutions to support patient communication and alleviate this …

View Full Text


  • Twitter @Roseliketheflwr, @cmpreik

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Provenance and peer review Commissioned; internally peer reviewed.