CoChat
Sign Up
Cited by 116Artificial Intelligence in Healthcare and EducationElectronic Health Records SystemsNursing Diagnosis and Documentation

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

ChatGPT's Ability to Assist with Clinical Documentation: A Randomized Controlled Trial

Baker, Hayden P., Dwyer, Emma, Kalidoss, Senthooran, Hynes, Kelly, Wolf, Jennifer, Strelzow, Jason A.·2024·Journal of the American Academy of Orthopaedic Surgeons
DOI 10.5435/jaaos-d-23-00474
Open this paper in CoChat — free account

Abstract

INTRODUCTION: Clinical documentation is a critical aspect of health care that enables healthcare providers to communicate effectively with each other and maintain accurate patient care records. Artificial intelligence tools, such as chatbots and virtual assistants, have the potential to assist healthcare providers in clinical documentation. ChatGPT is an artificial intelligence conversational model that generates human-like responses to text-based prompts. In this study, we sought to investigate ChatGPT's ability to assist with writing a history of present illness based on standardized patient histories. METHODS: A blinded, randomized controlled study was conducted to compare the use of typing, dictation, and ChatGPT as tools to document history of present illness (HPI) of standardized patient histories. Eleven study participants, consisting of medical students, orthopaedic surgery residents, and attending surgeons, completed three HPIs using a different documentation technique for each one. Participants were randomized into cohorts based on the type of documentation technique. Participants were asked to interview standardized patients and document the patient's history of present illness using their assigned method. RESULTS: ChatGPT was found to be intermediate for speed; dictation was fastest, but produced markedly longer and higher quality patient histories based on Physician Documentation Quality Instrument score compared with dictation and typing. However, ChatGPT included erroneous information in 36% of the documents. Poor agreement existed on the quality of patient histories between reviewers. DISCUSSION: Our study suggests that ChatGPT has the potential to improve clinical documentation by producing more comprehensive and organized HPIs. ChatGPT can generate longer and more detailed documentation compared with typing or dictation documentation methods. However, additional studies are needed to investigate and address concerns regarding privacy, bias, and accuracy of information.

Overview

Integrity signals

Registry

Crossref · 10.5435/jaaos-d-23-00474

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 7 references

Research works printed but not linked: 5

  1. Everything you need to know, Springboard Blog
  2. Ruby, 2024, ChatGPT statistics for 2023: Comprehensive facts and data, Demand Sage
  3. Optimizing Language models for dialogue, OpenAI
  4. Marr, Revolutionizing healthcare: The top 14 Uses of ChatGPT in medicine and wellness, Forbes
  5. Broder, 2023, AI miracles won't transform healthcare … but another miracle will, tHEORetically speaking

Cited by

Sorted by citations

Items 101–116 of 116

Related

See all

Metadata

Authors
Baker, H. P., Dwyer, E., Kalidoss, S., Hynes, K., Wolf, J., & Strelzow, J. A.
Affiliations
University of Chicago (US)
Corresponding author
Baker, Hayden P.
ORCID
Venue
Journal of the American Academy of Orthopaedic Surgeons
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2023-11-17
Volume
32
Issue
3
Pages
123-129
ISSN
  • 1067-151X (ISSN-L)
  • 1940-5480
DOI
10.5435/jaaos-d-23-00474
OpenAlex
W4388753652
Cited by
115
References
7
Citations by year
2026: 30 · 2025: 56 · 2024: 29
FWCI
4.59
Type
journal article
Language
en
Open access
closed
Locations
  • Journal of the American Academy of Orthopaedic Surgeons (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
  • Health Sciences › Nursing › Research and Theory › Nursing Diagnosis and Documentation
Keywords
ChatGPT, clinical documentation, history of present illness, artificial intelligence in healthcare, dictation, typing, documentation quality, standardized patients, orthopaedic residents, medical students
MeSH terms
Artificial Intelligence, Communication, Documentation, Health Facilities, Humans, Surgeons

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review