EUVIMEDOdkrijte EUVIMED
Open access

Evaluating AI-Generated Geriatric Case Studies for Interprofessional Education: Systematic Analysis Across 5 Platforms

Bewertung KI-generierter geriatrischer Fallstudien für interprofessionelle Bildung: systematische Analyse über 5 Plattformen

Nicole Ruggiano iD, Sudikshya Sahoo iD, Ava Brashear iD, Uche Nwatu iD, Amie Brunson iD, Hyunjin Noh iD, Heather Cole iD, Robert McKinney iD, C Victoria Framil Suarez iD, Ellen L Brown iD, Suzanne Prevost iD

JMIR Medical Education · 2026-01-30 · 12 · e83085

DOI: 10.2196/83085 ↗

Auf einen Blick

Fünf KI-Plattformen erzeugten je 10 geriatrische Fallstudien. Die Qualität variierte; ChatGPT schnitt im Mittel am besten ab, Grok am schlechtesten.

Fragestellung

Wie gut erzeugen 5 generative KI-Plattformen geriatrische Fallstudien für die interprofessionelle Bildung in Bezug auf Qualität, Genauigkeit und Bias?

Methode

10 geriatrische Fallstudien wurden mit demselben Prompt auf 5 Plattformen generiert; jede Fallstudie wurde von 3 Teammitgliedern mit dem SSET bewertet.

Ergebnisse

Je Plattform 10 einzigartige Fallstudien. ChatGPT hatte die höchste Gesamtbewertung (Mittel 3,27; 95 %-KI 2,95–3,59), Grok die niedrigste (Mittel 1,61; 95 %-KI 0,71–2,51).

Einschränkungen

Einige Fälle waren nicht realistisch; bestimmte ältere Patient:innengruppen und häufige Erkrankungen waren unterrepräsentiert oder fehlten.

Schlussfolgerung der Autor:innen

Die Studie liefert die erste systematische Bewertung mehrerer generativer KI-Plattformen zur Fallstudienerzeugung mit SSET und gibt evidenzbasierte Hinweise zur Auswahl und Nutzung von KI-Tools.

Kernaussagen

  • ChatGPT erhielt die höchste SSET-Gesamtbewertung
  • Grok erhielt die niedrigste SSET-Gesamtbewertung
  • Fallinhalte waren meist korrekt, aber teils unrealistisch

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Journal article in JMIR Medical Education, published online on 2026-01-30. Written by Nicole Ruggiano and 10 co-authors. Institution: School of Social Work, University of Alabama, Tuscaloosa, AL, United States. Major MEDLINE topics: Geriatrics, Interprofessional Education, Artificial Intelligence, Simulation Training. Cited 4 times so far (Crossref); 39 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Simulation-based learning (SBL) has become standard practice in educating health care professionals to apply their knowledge and skills in patient care. While SBL has demonstrated its value in education, many educators find the process of developing new, unique scenarios to be time-intensive, creating limits to the variety of issues students may experience within educational settings. Generative artificial intelligence (AI) platforms, such as ChatGPT (OpenAI), have emerged as a potential tool for developing simulation case studies more efficiently, though little is known about the performance of AI in generating high-quality case studies for interprofessional education.

Objective

This study aimed to generate geriatric case scenarios across 5 AI platforms by a transdisciplinary team and systematically evaluate them for quality, accuracy, and bias.

Methods

Ten geriatric case studies were generated using the same prompt from 5 different generative AI platforms (N=50): ChatGPT, Claude (Anthropic AI), Copilot (Microsoft), Gemini (Google), and Grok (xAI). An evaluation tool was developed to collect evaluative data to assess the content and quality of each case, sociodemographic data of the featured patient, the appropriateness of each case for interprofessional education, and potential bias. Case quality was evaluated using the Simulation Scenario Evaluation Tool (SSET). Each case was evaluated by 3 team members who had experience in SBL education. Assessment scores were averaged, and qualitative responses were extracted to triangulate patterns found in the quantitative data.

Results

While each AI platform was able to generate 10 unique case studies, the quality of studies varied within and across platforms. Generally, evaluators felt that the content in the cases was accurate, though some cases were not realistic. Some patient populations and common conditions among older adults were underrepresented or absent across the cases. All cases were set within traditional health care settings (eg, hospitals and routine medical visits). No cases featured home-based care. Based on the average SSET scores, reviewers assessed ChatGPT to be the highest overall performer (mean 3.27, SD 0.45, 95% CI 2.95-3.59) while Grok received the lowest scores (mean 1.61, SD 1.26, 95% CI 0.71-2.51). Platforms performed best at generating learning objectives (mean 3.35, SD 1.08, 95% CI 3.04-3.65) and lowest on their ability to describe supplies and materials that may be available in hypothetical scenarios (mean 1.27, SD 0.84, 95% CI 1.03-1.51).

Conclusions

This study is the first to systematically evaluate and compare multiple generative AI platforms for case study generation using a validated assessment tool (SSET) and provides evidence-based guidance on selecting and using AI tools effectively. The findings offer practical direction for educators navigating available generative AI tools to enhance training for health care professionals, including specific strategies for prompt engineering that can improve the quality of SBL resources in interprofessional education. These insights enable educators to leverage AI capabilities while maintaining pedagogical rigor.

Subjects

MeSH terms (MEDLINE)

GeriatricsInterprofessional EducationArtificial IntelligenceSimulation TrainingHumansGenerative Artificial Intelligence

Author keywords

chatbotsgenerative artificial intelligencegeriatric nursinginterprofessional educationpatient simulations

Authors and institutions

  • School of Social Work, University of Alabama, Tuscaloosa, AL, United States.
  • Department of Kinesiology, College of Education, University of Alabama, Tuscaloosa, AL, United States.
  • Capstone College of Nursing, University of Alabama, Tuscaloosa, AL, United States.
  • College of Community Health Sciences, University of Alabama, Tuscaloosa, AL, United States.
  • Nicole Wertheim College of Nursing and Health Sciences, Florida International University, Miami, AL, United States.

ORCID profiles: Nicole Ruggiano, Sudikshya Sahoo, Ava Brashear, Uche Nwatu, Amie Brunson, Hyunjin Noh, Heather Cole, Robert McKinney, C Victoria Framil Suarez, Ellen L Brown, Suzanne Prevost

Cite

APA

Ruggiano, N., Sahoo, S., Brashear, A., Nwatu, U., Brunson, A., Noh, H., Cole, H., McKinney, R., Framil Suarez, C. V., Brown, E. L., & Prevost, S. (2026). Evaluating AI-Generated Geriatric Case Studies for Interprofessional Education: Systematic Analysis Across 5 Platforms. JMIR Medical Education, 12, e83085. https://doi.org/10.2196/83085

Vancouver

Ruggiano N, Sahoo S, Brashear A, Nwatu U, Brunson A, Noh H, et al. Evaluating AI-Generated Geriatric Case Studies for Interprofessional Education: Systematic Analysis Across 5 Platforms. JMIR Medical Education. 2026;12:e83085. doi:10.2196/83085

BibTeX
@article{Ruggiano2026,
  author = {Ruggiano, Nicole and Sahoo, Sudikshya and Brashear, Ava and Nwatu, Uche and Brunson, Amie and Noh, Hyunjin and Cole, Heather and McKinney, Robert and Framil Suarez, C Victoria and Brown, Ellen L and Prevost, Suzanne},
  title = {Evaluating AI-Generated Geriatric Case Studies for Interprofessional Education: Systematic Analysis Across 5 Platforms},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e83085},
  doi = {10.2196/83085}
}
Start for free →