EUVIMEDObjevte EUVIMED
Open access

Generative Language Models and Open Notes: Exploring the Promise and Limitations

Charlotte Blease iD, John Torous iD, Brian McMillan iD, Maria Hägglund iD, Kenneth D Mandl iD

JMIR Medical Education · 2024

DOI: 10.2196/51183 ↗

At a glance

Journal article in JMIR Medical Education, 2024. Written by Charlotte Blease and 4 co-authors. Institution: Department of Women's and Children's Health, Uppsala University, Uppsala, Sweden. Major MEDLINE topics: Artificial Intelligence, Language. Cited 43 times so far (Crossref); 65 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Patients’ online record access (ORA) is growing worldwide. In some countries, including the United States and Sweden, access is advanced with patients obtaining rapid access to their full records on the web including laboratory and test results, lists of prescribed medications, vaccinations, and even the very narrative reports written by clinicians (the latter, commonly referred to as “open notes”). In the United States, patient’s ORA is also available in a downloadable form for use with other apps. While survey studies have shown that some patients report many benefits from ORA, there remain challenges with implementation around writing clinical documentation that patients may now read. With ORA, the functionality of the record is evolving; it is no longer only an aide memoire for doctors but also a communication tool for patients. Studies suggest that clinicians are changing how they write documentation, inviting worries about accuracy and completeness. Other concerns include work burdens; while few objective studies have examined the impact of ORA on workload, some research suggests that clinicians are spending more time writing notes and answering queries related to patients’ records. Aimed at addressing some of these concerns, clinician and patient education strategies have been proposed. In this viewpoint paper, we explore these approaches and suggest another longer-term strategy: the use of generative artificial intelligence (AI) to support clinicians in documenting narrative summaries that patients will find easier to understand. Applied to narrative clinical documentation, we suggest that such approaches may significantly help preserve the accuracy of notes, strengthen writing clarity and signals of empathy and patient-centered care, and serve as a buffer against documentation work burdens. However, we also consider the current risks associated with existing generative AI. We emphasize that for this innovation to play a key role in ORA, the cocreation of clinical notes will be imperative. We also caution that clinicians will need to be supported in how to work alongside generative AI to optimize its considerable potential.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceLanguageHumansCommunicationDocumentationEmpathy

Author keywords

ChatGPTOpen Notesclinical documentationcommunication tooldocumentationempathygenerative language modelslanguage modellarge language modelsmedical educationonline record accesspatient-centered care

Authors and institutions

  • Department of Women's and Children's Health, Uppsala University, Uppsala, Sweden.
  • Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA, United States.
  • Centre for Primary Care and Health Services Research, University of Manchester, Manchester, United Kingdom.
  • Medtech Science & Innovation Centre, Uppsala University Hospital, Uppsala, Sweden.
  • Computational Health Informatics Program, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.

ORCID profiles: Charlotte Blease, John Torous, Brian McMillan, Maria Hägglund, Kenneth D Mandl

Cite

APA

Blease, C., Torous, J., McMillan, B., Hägglund, M., & Mandl, K. D. (2024). Generative Language Models and Open Notes: Exploring the Promise and Limitations. JMIR Medical Education. https://doi.org/10.2196/51183

Vancouver

Blease C, Torous J, McMillan B, Hägglund M, Mandl KD. Generative Language Models and Open Notes: Exploring the Promise and Limitations. JMIR Medical Education. 2024. doi:10.2196/51183

BibTeX
@article{Blease2024,
  author = {Blease, Charlotte and Torous, John and McMillan, Brian and Hägglund, Maria and Mandl, Kenneth D},
  title = {Generative Language Models and Open Notes: Exploring the Promise and Limitations},
  journal = {JMIR Medical Education},
  year = {2024},
  doi = {10.2196/51183}
}
Start for free →