EUVIMEDEUVIMED entdecken
Qualitative StudieOpen Access

Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study

Joseph Cross iD, Tarron Kayalackakom iD, Raymond E Robinson iD, Andrea Vaughans iD, Roopa Sebastian iD, Ricardo Hood iD, Courtney Lewis iD, Sumanth Devaraju iD, Prasanna Honnavar iD, Sheetal Naik iD, Jillwin Joseph iD, Nikhilesh Anand iD und 6 weitere

JMIR Medical Education · 20.05.2025 · 11 · e63353-e63353

DOI: 10.2196/63353 ↗

Kurz gefasst

Qualitative Studie in der Zeitschrift JMIR Medical Education, online erschienen am 20.05.2025. Verfasst von Joseph Cross und 17 weiteren Autor:innen. Beteiligte Einrichtung: Medical University of the Americas, PO Box 701, Charlestown, Saint Kitts and Nevis, 1 9788629500 ext 364. Hauptthemen laut MEDLINE: Students, Medical, Patient Simulation. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Standardized patients (SPs) have been crucial in medical education, offering realistic patient interactions to students. Despite their benefits, SP training is resource-intensive and access can be limited. Advances in artificial intelligence (AI), particularly with large language models such as ChatGPT, present new opportunities for virtual SPs, potentially addressing these limitations.

Objectives

This study aims to assess medical students’ perceptions and experiences of using ChatGPT as an SP and to evaluate ChatGPT’s effectiveness in performing as a virtual SP in a medical school setting.

Methods

This qualitative study, approved by the American University of Antigua Institutional Review Board, involved 9 students (5 females and 4 males, aged 22‐48 years) from the American University of Antigua College of Medicine. Students were observed during a live role-play, interacting with ChatGPT as an SP using a predetermined prompt. A structured 15-question survey was administered before and after the interaction. Thematic analysis was conducted on the transcribed and coded responses, with inductive category formation.

Results

Thematic analysis identified key themes preinteraction including technology limitations (eg, prompt engineering difficulties), learning efficacy (eg, potential for personalized learning and reduced interview stress), verisimilitude (eg, absence of visual cues), and trust (eg, concerns about AI accuracy). Postinteraction, students noted improvements in prompt engineering, some alignment issues (eg, limited responses on sensitive topics), maintained learning efficacy (eg, convenience and repetition), and continued verisimilitude challenges (eg, lack of empathy and nonverbal cues). No significant trust issues were reported postinteraction. Despite some limitations, students found ChatGPT as a valuable supplement to traditional SPs, enhancing practice flexibility and diagnostic skills.

Conclusions

ChatGPT can effectively augment traditional SPs in medical education, offering accessible, flexible practice opportunities. However, it cannot fully replace human SPs due to limitations in verisimilitude and prompt engineering challenges. Integrating prompt engineering into medical curricula and continuous advancements in AI are recommended to enhance the use of virtual SPs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Students, MedicalPatient SimulationHumansQualitative ResearchFemaleAdultMaleMiddle AgedYoung AdultArtificial IntelligenceSurveys and QuestionnairesEducation, Medical, UndergraduateGenerative Artificial Intelligence

Stichwörter der Autor:innen

AIChatGPTLLMassessmentdiagnosticeffectivenessflexibilitymedical educationmedical schoolqualitativestandardized patientstandardized patientsvirtual patient

Autor:innen und Institutionen

  • Medical University of the Americas, PO Box 701, Charlestown, Saint Kitts and Nevis, 1 9788629500 ext 364.
  • Department of Education Enhancement, College of Medicine, American University of Antigua, St Johns, Antigua and Barbuda.
  • Department of Health Informatics, School of Professional Studies, Northwestern University, Evanston, IL, United States.
  • Department of Biochemistry, Cell Biology and Genetics, College of Medicine, American University of Antigua, Basseterre, Antigua and Barbuda.
  • Department of Medical Education, School of Medicine, University of Texas Rio Grande Valley, Edinburgh, TX, United States.
  • School of Medicine, Xavier University, Orangestad, Aruba.

ORCID-Profile: Joseph Cross, Tarron Kayalackakom, Raymond E Robinson, Andrea Vaughans, Roopa Sebastian, Ricardo Hood, Courtney Lewis, Sumanth Devaraju, Prasanna Honnavar, Sheetal Naik, Jillwin Joseph, Nikhilesh Anand, Abdalla Mohammed, Asjah Johnson, Eliran Cohen, Teniola Adeniji, Aisling Nnenna Nnaji, Julia Elizabeth George

Zitieren

APA

Cross, J., Kayalackakom, T., Robinson, R. E., Vaughans, A., Sebastian, R., Hood, R., Lewis, C., Devaraju, S., Honnavar, P., Naik, S., Joseph, J., Anand, N., Mohammed, A., Johnson, A., Cohen, E., Adeniji, T., Nnenna Nnaji, A., & George, J. E. (2025). Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study. JMIR Medical Education, 11, e63353-e63353. https://doi.org/10.2196/63353

Vancouver

Cross J, Kayalackakom T, Robinson RE, Vaughans A, Sebastian R, Hood R, et al. Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study. JMIR Medical Education. 2025;11:e63353-e63353. doi:10.2196/63353

BibTeX
@article{Cross2025,
  author = {Cross, Joseph and Kayalackakom, Tarron and Robinson, Raymond E and Vaughans, Andrea and Sebastian, Roopa and Hood, Ricardo and Lewis, Courtney and Devaraju, Sumanth and Honnavar, Prasanna and Naik, Sheetal and Joseph, Jillwin and Anand, Nikhilesh and Mohammed, Abdalla and Johnson, Asjah and Cohen, Eliran and Adeniji, Teniola and Nnenna Nnaji, Aisling and George, Julia Elizabeth},
  title = {Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study},
  journal = {JMIR Medical Education},
  year = {2025},
  volume = {11},
  pages = {e63353--e63353},
  doi = {10.2196/63353}
}
Kostenlos starten →