Multiturn Large Language Model–Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review
Multiturn-LLM-basierte dialogische Agenten für Patient:innen mit Krebs und Angehörige: Scoping Review
JMIR Cancer · 21.07.2026 · 12 · e96241-e96241
DOI: 10.2196/96241 ↗Auf einen Blick
Das Scoping Review fand 8 Studien zu LLM-basierten Multiturn-Chatbots für Patient:innen mit Krebs und informelle Pflegepersonen. Die Arbeiten waren überwiegend prototypisch und berichteten uneinheitlich zu Sicherheit und Transparenz.
Fragestellung
Wie ist die Forschungslage zu LLM-basierten Multiturn-Chatbots für Patient:innen mit Krebs und informelle Pflegepersonen hinsichtlich Design, Zweck, Evaluation, Sicherheit und Transparenz?
Methode
Scoping Review nach JBI und PRISMA-ScR; Suche in 6 Datenbanken für Studien von Januar 2022 bis Januar 2026, ergänzend IEEE Xplore und ACM Digital Library im Mai 2026.
Ergebnisse
8 Studien erfüllten die Kriterien. Meist ging es um Prototypen; ChatGPT-basierte Modelle waren am häufigsten. Evaluationen variierten, klinische Endpunkte wurden selten geprüft.
Einschränkungen
Keine Studien prüften Interaktionsmerkmale wie Gesprächskontinuität oder Kontextverbleib; nur 2 berichteten einen Gesprächsspeicher. Sicherheits- und Transparenzangaben waren oft lückenhaft.
Schlussfolgerung der Autor:innen
Die Autor:innen sehen das Feld als noch früh entwickelt mit prototyporientierter Entwicklung, heterogenen Design- und Evaluationsansätzen sowie inkonsistenter Sicherheits- und Transparenzberichterstattung.
Kernaussagen
- 8 Studien zu Multiturn-Chatbots in der Onkologie
- Meist Prototypen; Fokus auf emotionale Unterstützung und Information
- Interaktionsqualität, Sicherheit und Transparenz oft unzureichend berichtet
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Scoping Review in der Zeitschrift JMIR Cancer, online erschienen am 21.07.2026. Verfasst von Yeongrok Jeong und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for World-leading Human-care Nurse Leaders for the Future by Brain Korea 21 (BK21) Four Project, College of Nursing, Research Institute of Nur…. Hauptthemen laut MEDLINE: Neoplasms, Caregivers. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Large language model (LLM)–based conversational agents are increasingly used in health care, yet their capacity to support genuine multiturn dialogue remains underexplored. In oncology, where patients and caregivers experience complex informational and emotional needs throughout the disease trajectory, conversational agents may support information provision, symptom consultation, and emotional assistance. However, research specifically examining multiturn conversational agents designed for patients with cancer and informal caregivers remains limited.
Objective
This scoping review aimed to map the research landscape of LLM-based multiturn conversational chatbots developed for patients with cancer and informal caregivers, focusing on system design, intervention purposes, evaluation approaches, safety considerations, and transparency of LLM-related components.
Methods
This scoping review followed the Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Six databases—PubMed, Embase, Scopus, Web of Science, CINAHL, and PsycINFO—were searched for studies published between January 2022 and January 2026, with supplementary searches conducted in IEEE Xplore Digital Library and ACM Digital Library in May 2026. Studies were included if they described LLM-based chatbots designed for patients with cancer or informal caregivers that supported multiturn conversational interaction. Two reviewers independently conducted the study selection and data extraction.
Results
Eight studies met the inclusion criteria. Most studies focused on prototype development, with limited research evaluating clinical outcomes. ChatGPT-based models were the most commonly used LLMs, and retrieval-augmented generation techniques were applied in several studies. Chatbots were primarily designed for emotional support or information provision. Evaluation approaches varied widely, including response quality, psychological outcomes, and user experience. However, no studies evaluated interaction-level characteristics such as conversational continuity or context retention, and only 2 studies reported any conversational memory mechanism. Reporting on safety risks, mitigation strategies, prompt design, model parameters, and adherence to LLM reporting guidelines was often limited or absent.
Conclusions
This scoping review identified only 8 studies on LLM-based multiturn conversational chatbots for patients with cancer and informal caregivers. The field remains at an early stage, characterized by prototype-oriented development, heterogeneous design and evaluation approaches, and inconsistent safety and transparency reporting. Future development should prioritize genuine conversational capability, safety management, and transparent reporting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for World-leading Human-care Nurse Leaders for the Future by Brain Korea 21 (BK21) Four Project, College of Nursing, Research Institute of Nursing Science, Seoul National University, 103 Daehak-ro, Jongno-gu, Seo…
- College of Nursing, Seoul National University, Seoul, Republic of Korea.
ORCID-Profile: Yeongrok Jeong, Hyejeon Cha, Eunyoung E Suh
Zitieren
APA
Jeong, Y., Cha, H., & Suh, E. E. (2026). Multiturn Large Language Model–Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review. JMIR Cancer, 12, e96241-e96241. https://doi.org/10.2196/96241
Vancouver
Jeong Y, Cha H, Suh EE. Multiturn Large Language Model–Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review. JMIR Cancer. 2026;12:e96241-e96241. doi:10.2196/96241
BibTeX
@article{Jeong2026,
author = {Jeong, Yeongrok and Cha, Hyejeon and Suh, Eunyoung E},
title = {Multiturn Large Language Model–Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review},
journal = {JMIR Cancer},
year = {2026},
volume = {12},
pages = {e96241--e96241},
doi = {10.2196/96241}
}
EUVIMED