EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access

Large Language Model–Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review

Große Sprachmodell-basierte virtuelle Patientensysteme für die Anamnese in der medizinischen Ausbildung: umfassende systematische Übersicht

Dongliang Li iD, Syaheerah Lebai Lutfi iD

JMIR Medical Informatics · 02.01.2026 · 14 · e79039

DOI: 10.2196/79039 ↗

Auf einen Blick

39 Studien zu LLM-basierten virtuellen Patientensystemen zeigten meist gute Ergebnisse für die Anamneseausbildung. Multimodale Eingaben und bestimmte Techniken verbesserten Dialog und diagnostische Genauigkeit.

Fragestellung

Wie leistungsfähig sind LLM-basierte virtuelle Patientensysteme für die Anamnese in der medizinischen Ausbildung?

Methode

Systematische Übersicht nach PRISMA 2020; 9 Datenbanken von 1. Januar 2020 bis 18. August 2025 durchsucht; multidimensionale Qualitäts- und Bias-Bewertung.

Ergebnisse

39 eingeschlossene Studien. Systeme simulierten vor allem Innere Medizin und psychische Erkrankungen. Top-k accuracy: 0,45–0,98; Halluzinationsrate: 0,31 %–5 %; SUS ≥80. Kleine Stichproben, inkonsistente Metriken und wenige Kontrollen schränkten die Generalisierbarkeit ein.

Einschränkungen

Moderates Bias-Risiko, inkonsistente Metriken, kleine Kohorten und begrenzte Datensatztransparenz.

Schlussfolgerung der Autor:innen

Die eingeschlossenen Studien zeigten ein moderates Bias-Risiko, inkonsistente Metriken, kleine Kohorten und begrenzte Datensatztransparenz. LLM-basierte Systeme bilden mehrere Krankheitsbilder gut ab, aber Multimorbidität unzureichend.

Kernaussagen

  • 39 Studien zu LLM-basierten virtuellen Patientensystemen
  • Top-k accuracy 0,45–0,98; Halluzinationsrate 0,31 %–5 %
  • Multimorbidität und seltene Erkrankungen waren selten vertreten

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

Kurz gefasst

Systematische Übersicht in der Zeitschrift JMIR Medical Informatics, online erschienen am 02.01.2026. Verfasst von Dongliang Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Intelligence & Software Engineering, School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia. Hauptthemen laut MEDLINE: Education, Medical, Large Language Models, Medical History Taking. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Large language models (LLMs), such as GPT-3.5 and GPT-4 (OpenAI), have been transforming virtual patient systems in medical education by providing scalable and cost-effective alternatives to standardized patients. However, systematic evaluations of their performance, particularly for multimorbidity scenarios involving multiple coexisting diseases, are still limited.

Objective

This systematic review aimed to evaluate LLM-based virtual patient systems for medical history-taking, addressing four research questions: (1) simulated patient types and disease scope, (2) performance-enhancing techniques, (3) experimental designs and evaluation metrics, and (4) dataset characteristics and availability.

Methods

Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020, 9 databases were searched (January 1, 2020, to August 18, 2025). Nontransformer LLMs and non–history-taking tasks were excluded. Multidimensional quality and bias assessments were conducted.

Results

A total of 39 studies were included, screened by one computer science researcher under supervision. LLM-based virtual patient systems mainly simulated internal medicine and mental health disorders, with many addressing distinct single disease types but few covering multimorbidity or rare conditions. Techniques like role-based prompts, few-shot learning, multiagent frameworks, knowledge graph (KG) integration (top-k accuracy 16.02%), and fine-tuning enhanced dialogue and diagnostic accuracy. Multimodal inputs (eg, speech and imaging) improved immersion and realism. Evaluations, typically involving 10-50 students and 3-10 experts, demonstrated strong performance (top-k accuracy: 0.45-0.98, hallucination rate: 0.31%–5%, System Usability Scale [SUS] ≥80). However, small samples, inconsistent metrics, and limited controls restricted generalizability. Common datasets such as MIMIC-III (Medical Information Mart for Intensive Care-III) exhibited intensive care unit (ICU) bias and lacked diversity, affecting reproducibility and external validity.

Conclusions

Included studies showed moderate risk of bias, inconsistent metrics, small cohorts, and limited dataset transparency. LLM-based virtual patient systems excel in simulating multiple disease types but lack multimorbidity patient representation. KGs improve top-k accuracy and support structured disease representation and reasoning. Future research should prioritize hybrid KG-chain-of-thought architectures integrated with open-source KGs (eg, UMLS [Unified Medical Language System] and SNOMED-CT [Systematized Nomenclature of Medicine - Clinical Terms]), parameter-efficient fine-tuning, dialogue compression, multimodal LLMs, standardized metrics, larger cohorts, and open-access multimodal datasets to further enhance realism, diagnostic accuracy, fairness, and educational utility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Education, MedicalLarge Language ModelsMedical History TakingHumans

Stichwörter der Autor:innen

history-takinglarge language modelmedical educationsimulated patientsvirtual patient

Autor:innen und Institutionen

  • Artificial Intelligence & Software Engineering, School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia.
  • Medical Informatics Department, College of Medicine and Health Sciences, Sultan Qaboos University, Al Seeb, Oman.

ORCID-Profile: Dongliang Li, Syaheerah Lebai Lutfi

Zitieren

APA

Li, D., & Lebai Lutfi, S. (2026). Large Language Model–Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review. JMIR Medical Informatics, 14, e79039. https://doi.org/10.2196/79039

Vancouver

Li D, Lebai Lutfi S. Large Language Model–Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review. JMIR Medical Informatics. 2026;14:e79039. doi:10.2196/79039

BibTeX
@article{Li2026,
  author = {Li, Dongliang and Lebai Lutfi, Syaheerah},
  title = {Large Language Model–Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e79039},
  doi = {10.2196/79039}
}
Kostenlos starten →